Security Now 1084: The Residential Proxy Threat

Summary

Security Now #1084: The Residential Proxy Threat (June 24, 2026)

Episode Overview

In this week’s episode of Security Now, host Steve Gibson and Leo Laporte tackle the rapidly escalating threat posed by residential proxy networks, explaining how millions of everyday consumer devices are being subverted to mask cybercrime and nation-state attacks. They cover the mechanics and risks of these proxies, the wider trends in cybersecurity accelerated by AI, fresh evidence of system vulnerabilities (including in Firefox), and the ongoing “zero-day” battle between Microsoft and the relentless researcher “Nightmare Eclipse.” The episode also includes segments on massive Fortinet VPN credential leaks, F5/Nginx emergency patches, and a refreshing look at customizing AI personalities, topped off with practical advice for home and enterprise security.

---

Main Discussion Topics

1. AI’s Double-Edged Sword in Cybersecurity

Key Points:

• Increasing concern in mainstream press (The Atlantic, Wall Street Journal) about AI’s impact on both sides: enabling better attack tools and more effective defense.
• Explosive increase in vulnerabilities discovered via AI (e.g., Claude Mythos, OpenAI’s GPT-5.5 cyber) but also in AI-powered attacks.
• Notable Quote:
  "What we know is that we haven't actually yet seen evidence of superhuman performance from any of the AI models. It's just endurance. If you got really good hackers and told them, 'We got a million dollars here for you,' they can do what the AI could do. It's not like the AI can do stuff no one has ever seen before." — Steve Gibson (09:38)
• The time between vulnerability disclosure and active exploitation is shrinking dramatically (from 700 days in 2020 to just 44 in 2025).
• OpenAI and Anthropic have withheld their most advanced models from public release due to offensive potential.

Timestamps

• [09:24] NSA reveals massive classified system breaches by Mythos AI in “hours, not weeks.”
• [20:53] The Atlantic mainstream coverage: “Assume you will be hacked.”

---

2. The Residential Proxy Threat

What are Residential Proxies?

Malware—increasingly pre-installed in consumer hardware (streaming boxes, digital frames), in apps, and in pirated software—secretly turns home devices into nodes for massive global proxy networks. These are then rented to cybercriminals or state actors, letting their attacks appear as if coming from normal U.S. households instead of overseas bad actors.

How Big Is the Problem?

• Estimated 20 million infected devices in the U.S. alone (Digital Citizens Alliance); Comcast identified 750,000 compromised household IP addresses.
• State actors from Russia, China, Iran, and North Korea now systematically use these networks to evade geofencing and detection.

Notable Quote:
"These are Trojan horses. What's chilling is what we learn about some of the way this is happening... More low cost consumer devices have shipped into the US with backdoor software preinstalled." — Steve Gibson (124:09)

Timestamps

• [123:49] — Introduction to the Wall Street Journal reporting on residential proxies
• [126:44] — Comcast investigates: 750,000 home/business IPs acting as proxies for Russian attacks
• [133:05] — How NAT routers and IoT isolation play into the threat

Attack Vectors & Techniques

• Malware pre-installed at the factory, pirated/illegitimate mobile apps, “free” games
• Outbound connections from home devices create persistent tunnels for command & control
• Attackers can use compromised devices to pivot into local networks and further compromise sensitive systems

Real-World Example

NSA, Microsoft, and Midnight Blizzard:
State actors routed attacks on Microsoft leadership emails via U.S.-based home proxies, frustrating attribution and allowing access that geofencing would otherwise block.

Defense Strategies

• Isolate IoT devices on dedicated VLANs or guest Wi-Fi networks with proper isolation.
• Minimize trust in third-party/off-brand devices, especially those sourced from less-regulated manufacturers.
• Use strong multi-factor authentication everywhere, especially on network border devices.

Notable Quote:
"750,000 IP addresses. Households and businesses... it was a back door into America, operating at an industrial scale." — Steve Gibson (128:16)

---

3. Massive Credential & Zero-Day Leaks

Fortinet/Fortigate VPN Credentials Leak

• The “Fortibleed” database, containing approx. 74,000 unique firewall URLs with admin credentials (including for major enterprises), surfaced — the result of large-scale brute-forcing.
• Affected: Chevron, Samsung, Comcast, Mercedes-Benz, Toyota, and many more, along with several governments.
• Many passwords were long and complex — not a sign of poor passwords, but attack scale/sophistication.

Urgent Recommended Action:

• Immediate password rotation
• Enforce MFA
• Remove Internet-exposed management interfaces

Timestamps

• [77:38] — Details and scope of the Fortinet credential breach

Ongoing Zero-Day Battle: "Nightmare Eclipse"

• Researcher repeatedly drops zero-days timed with Patch Tuesday. Latest: “Rogue Planet” (Microsoft Defender elevation of privilege).
• Ongoing dispute with Microsoft, who is now warning of possible legal action over disclosure practices.
• Microsoft confirmed they are working on a patch, but did not acknowledge the researcher directly.

---

4. Latest AI & Security Threats in the Wild

Firefox Emergency Updates Missed by AI

• Even after Mozilla used Claude Mythos to fix ~400 bugs, a new batch of serious vulnerabilities (remote code execution, sandbox escapes) required immediate attention in version 152.
• Exploit chains allow full system compromise just by visiting a malicious site.

Notable Quote: "Looks like Mythos needs to run a few more times on Firefox." — Listener Joey Albert, quoted by Steve Gibson (48:48)

F5/Nginx Emergency Updates

• Two critical code execution vulnerabilities in NGINX (and multiple high-severity issues) — immediate patching recommended for a web server used by the Fortune 500.

---

5. AI Potpourri: Customizing AI Personality

• Listener Will Kelly shared a creative approach: turning Claude into “Agent Smith” from The Matrix, making responses chillingly menacing and unmistakably inhuman.
• Demonstrated how deeply the pre-prompt/instructional personality settings can transform an AI’s tone and demeanor.

Memorable Agent Smith Responses:

• (On naming a kitten)
  "You've acquired a small predator and now require my assistance to label it. How quaintly characteristic of your species to domesticate a creature that would, given sufficient scale, regard you as prey..." — “Claude as Agent Smith” (108:00)
• (On the woodchuck riddle)
  "Ah, of all the questions your species would pose ... you select a nursery rhyme. How perfectly predictable of you..." (112:48)

Timestamps

• [104:18] — Introduction to the AI Potpourri section and listener’s technique

---

Key Quotes & Memorable Moments

• "It's one of the most worrying problems the telecommunications company has seen." — Comcast’s Head of Information Security, on residential proxies (126:03)
• "I have very little sympathy for mega corporations who rely upon the charity of other researchers to find the flaws that should never have shipped in their products to begin with." — Steve Gibson (21:17)
• "We're not spending the money because these are hard things to find. AI makes them easier to find. So whose AI will be the first to discover a previously unknown problem? The good guys or the bad guys?" — Steve Gibson (41:19)

---

Practical Takeaways & Advice

• For Enterprises:

  • Regular patching is critical, but not enough: ensure vulnerable interfaces are not Internet-exposed and multi-factor authentication is mandatory.
  • Audit all VPN access methods, especially Fortinet/Fortigate appliances
  • Be proactive about network segmentation and limiting lateral movement

• For Individuals/Home Users:

  • Segment IoT devices onto isolated Wi-Fi or VLANs, with strict egress filtering if possible ([155:38])
  • Treat generic/unbranded smart devices, especially imported ones, as potentially hostile by default
  • Use password managers, stay vigilant for phishing, and keep devices fully updated
  • Check with online tools (e.g., Hudson Rock Fortinet lookup) if your systems might be affected by major credential leaks (HudsonRock.com/fortinet)

• For Developers:

  • Be aware that attack techniques (such as reverse engineering and re-packaging of mobile apps) are getting more sophisticated — use anti-tampering and monitoring services

---

The Bottom Line

Steve and Leo’s central message: The age of industrial-scale residential proxy abuse is here, and it's a force multiplier for cybercriminals and state actors alike. Combined with the AI arms race, this creates an unprecedented and rapidly evolving threat landscape. The effective defenses remain: rapid patching, improving software quality, enforcing strong authentication, and taking network hygiene (especially IoT segregation) seriously. The “bad guys” are now everywhere — including your grandma’s digital photo frame.

---

Episode Segments & Timestamps

• [00:00] - Episode introduction, overview of topics
• [09:24] - NSA breach by AI, the limits of current AI tools
• [20:53] - AI and the mainstream press: The Atlantic’s "Assume You Will Be Hacked"
• [41:19] - The patching dilemma and software’s insecure history
• [48:48] - Firefox: New vulnerabilities “missed” by AI discovery tools
• [62:15] - The ongoing “Nightmare Eclipse” zero-day saga
• [77:38] - Fortinet/Fortigate giant credential leak ("Fortibleed")
• [104:18] - AI Potpourri: Listener customization of Claude’s personality
• [123:49] - Residential proxies: Wall Street Journal exposé and analysis
• [155:27] - Practical defense: VLANs, isolated networks, IoT risk management

---

References & Resources

• Hudson Rock Fortinet Leak Checker
• The Atlantic: "Assume You Will Be Hacked"
• Wall Street Journal: "How Hackers Found a Back Door into the American Living Room"
• Mozilla Security Advisories for Firefox

---

For further reading, full show notes, and security tools, visit Steve Gibson’s GRC.com.

Transcript

[Leo Laporte]

It's time for Security now. Steve Gibson is here. Lots to talk about some more vulnerabilities in Firefox. Steve has a theory about Microsoft's AI. F5 has some emergency updates. And we'll talk about malicious bad guys in your own network, the malicious proxy networks. That's all coming up next. Security now

[Steve Gibson]

podcasts you love from people you trust.

[Leo Laporte]

This is Twit. This is Security now with Steve Gibson. Episode 1084 recorded Tuesday, June 23, 2026. The residential proxy threat. It's time for Security now. Yay. You've been waiting all week. Tuesday's here and so is Steve Gibson, the man of the day, of the, of the minute, of the second. It is time to talk about privacy, security, computers and all of that. What are you doing there?

[Steve Gibson]

I've lost my fingerprints, apparently.

[Leo Laporte]

That's not good. Or is it?

[Steve Gibson]

No, my, my iPads, I still have some iPads that are finger rather than.

[Leo Laporte]

The mini is still that way and I prefer that especially.

[Steve Gibson]

Yeah, I like it a lot and I, because I got one, I kept waiting to like, see if Apple was going to rev it and it's like, okay, I, I can't because the one I had, if you took it off of the plug, it was on life support and it would just. Well, actually what happened was the. Some of the software that I want to use, like Claude's iOS app and the dumb, the dumb thing from my thermostats, they don't run on the iOS that's so old, which is the late, the last one that, that mini that that pad will operate on. So it's like, okay, I was kind of forced to forward anyway, so. Because I've been, I've been terminating Cat 5 cables and, you know, untwisting twisted pairs and straightening them out and pushing them through the Cat 5 connector. I, I've kind of worn off my fingerprints in the last couple weeks. So anyway, that's what's going on. We're going to talk about the surprisingly serious and growing threat from residential proxies. We've, we've been touching on this recently because it's kind of been in the news. Well, there's essentially a recent explosion in the use of proxy networks because bad guys need to arrange to appear somewhere else. There's. There's a bin on. We've heard me talking about, like, why would you let Russians coming. You know, people in Russian IP space have any idea that you have an SSH server? Sure. You got it protected with certificates and a really crazy password. And multi factor authentication. But why should your SSH server even accept a connection from Russia? When are you planning to visit there? So the point is that there's an increasing awareness of the value of geo locking, IP filtration, which means that the bad guys have to work around that. How do they do that? They bounce their traffic off of unwitting people in the country that they want to target. Anyway, lots going on there. We're going to talk about there's. It was interesting to me this, this awareness of the growing concern of AI's impact on cyber attacks is hitting the mainstream press. The Wall Street Journal had an article that I want to share parts of and, and, and interject some thoughts into. Also it looks like maybe Mythos missed some important vulnerabilities in Firefox, which is interesting because what Also every recent patch Tuesday has had an attack by the Microsoft's nemesis nightmare Eclipse. And that happened again. So we'll take a look at that.

[Leo Laporte]

He is really a thorn in the side.

[Steve Gibson]

Oh my God. It's like why doesn't someone at Microsoft just say okay, what do you want? Like we're sorry. Would you like a public apology? Would you like a Winnebago? You know, what can we do for you to solve this problem? Because I mean it's got to be expensive for them. They're, you know, they're rattling their sabers and threatening and that, that threat really did rub me the wrong way as well as most of the rest of the security industry because they're threatening someone over revealing something in software they have shipped containing about a bug that they put into the software. It's like how is that this guy's fault for like not, you know, yes, he's not going by the unwritten rules, but they're unwritten and you know, we just sort of made them up to help you Microsoft, not for you to like you know, sue people over them. I mean I'm sure that if you dissected their license agreement in the fine print it would say something like, you know, you agree by ever letting this software touch your computer that blah blah blah blah prop. So you know, there's probably a technical basis for it, but that's not the way to solve the problem. Anyway, we've got a really interesting massive store of known to be valid fortigate VPN credentials found. You know Fortinet is a, is a leading supplier of of border gateway devices for a gate is their VPN server and someone's been getting into them and hoarding the credentials. We'll Take a look at that. Also, F5, which purchased the company that was. That was creating and publishing the nginx web server. They just pushed some emergency updates which are important. I've decided to introduce what I will call the AI Potpourri section of the podcast, much as we've had, you know, listener feedback and so forth, which of course will always have, because I wanted a place to talk about just random AI stuff that was of interest in this case. It's a listener of ours and I may have referred to him in, like last week or the week before because it was interesting. He arranged to. Will is his first name. We'll get to him deeply altering his AI's personality, instructing it to basically act like Agent Smith from the Matrix. I do remember that I talked about it last week. I have in detail what he told his AI. And then I asked him for some sample prompts and so that I could see. So that we could all see how the AI replied. It's pretty fun. So I'm going to share that and I have a feeling that a lot of our listeners are going to take this up. Then we're going to, as I said, take a close look at the explosion in malicious proxy networks. And then just in the news, as I was finishing this, a judge in Canada okayed something that I didn't think we would see. So lots to talk about. And of course we have a picture of the week, which will be fun. We've wandered far afield from anything having to do with security. Like, you know, okay, the gate in the middle of the field that was. Or. And the sheeps standing behind it patiently waiting for it to open. You know, I guess we'd already sort of lost the thread there, but this one's fun for anyone who's married will understand this.

[Leo Laporte]

I have a question for you before we get to the picture of the week and our first sponsor of the week, and I just wanted to run something by you. The Economist is reporting that in testimony to the Senate, the head of the NSA told Senator Mark Warner that one of the reasons Mythos and Fable were banned by the Trump administration is that it had breached almost all of the NSA's classified systems within a few hours during a Red Team test. Now, I have no reason to think that Joshua Rudd, the head of the NSA and U.S. cyber Command, was lying to Mark Warner or that Mark Warner misrepresented it. Rudd, according to the Economist, told Warner that this tool broke into almost all of our classified systems, not in weeks, but in hours. Except that that tells me the NSA's classified systems are buggy as hell. Yeah.

[Steve Gibson]

I'm, like, disturbed that that's not.

[Leo Laporte]

To me, it's not disturbing that Mythos did that. Mythos is capable of that. It's disturbing that they had such buggy, classified systems.

[Steve Gibson]

And what we know is that we haven't actually yet seen evidence of superhuman performance from any of the AI Most.

[Leo Laporte]

That's what everybody's saying.

[Steve Gibson]

It's just endurance. If you got really good hackers and told them, well, you're you. We got a million dollars here for you, you know, mo. You know, sufficiently motivate them, they can do what the AI could do. It's not like the AI can do stuff no one has ever seen before.

[Leo Laporte]

Yeah.

[Steve Gibson]

So that's really interesting.

[Leo Laporte]

Yeah. It would certainly explain the ban. But as. And we had Alex Stamos last week on intelligent machines, except they're not that

[Steve Gibson]

far ahead of everything.

[Leo Laporte]

That's what Stamos has been saying. And Stamos, by the way, that letter, it's freefable.org, that open letter to the White House had signatories, hundred signatories, including Paul Vicksie, one of the founders of the Internet. Yeah. I mean, just like, really good cryptographers.

[Steve Gibson]

A real who's who.

[Leo Laporte]

It was a who's who. And one of the contentious was it's not doing anything that other models can't do.

[Steve Gibson]

Right.

[Leo Laporte]

In fact, OpenAI apparently has its next generation of ChatGPT ready to go 5, 6. That has. They call it ChatGPT Cyber that does many of the same things. So.

[Steve Gibson]

And I have a sense that although Microsoft is not talking about that codename EM Dash, which I wish they would just rename from what we know of it, I think it beats all of this.

[Leo Laporte]

It found a lot of those vulnerabilities from the giant patch Tuesday last week.

[Steve Gibson]

I think what Microsoft has is already in the next generation class. They've talked about letting other people experiment with it and turn it loose. So. So the point is, I mean, there is so much money and so much focus and so much promise that you. I don't think I've ever seen the human race more motivated about something. I really. Except maybe solving Covid like a. Like we. We need to, you know, cure Covid quickly, get a vaccine. You know, there was mobilization, but. But here it's like, wow,

[Leo Laporte]

it's going to be an interesting year, isn't it, Steve?

[Steve Gibson]

Oh, boy.

[Leo Laporte]

Aren't you glad you're watching security now? And if you're not A subscriber to the show yet, you really ought to be. It's free. Just subscribe on your favorite podcast client. And if you want to support us, of course, join the club. Twitter, TV Club Twit, or you can pay for individual episodes in Apple's podcast app. I think Spotify also has that built in. We'd prefer, of course, you subscribe to the whole network and support everything we do. But I think more important, more and more important, the stuff we're doing here, not only in security now, but in intelligent machines and on the Twitter flagship show. This is going to be a very interesting 20, 26 and beyond. We will get to the picture of the week, something every, you said every husband will understand, will relate to in just a moment.

[Steve Gibson]

And actually, and actually the wives as well. But it's about being married.

[Leo Laporte]

Essentially, it's about being married. Oh, boy, I can't wait to. I haven't looked at it. I've been saving it. That's coming up. But first, a word from our sponsor, Doppel. And this is very timely, let me tell you. You know that voicemail message you got, that urgent message, Maybe it is from your CEO, sounds exactly like your CEO, but maybe it's a deep fake trying to target your business. And that's the problem. AI can impersonate trusted individuals. And I've played for you in the past. I could play it for you again. The very scary. This was an eye opener for me. Audio that was quickly generated was generated almost instantly with four minutes of audio of my voice by our own Anthony Nielsen using a. He didn't even use like a Frontier model. He used a model running on his own computer to generate. Well, I'll play. I'll just play a little bit of it for you so you can hear. He used Quinn, the Chinese model, an older Quinn Quinn 3, to do this. Hey, Burke, this is definitely not Leo asking you to buy gift cards. But seriously, can you grab me 100 Apple gift cards? That's ex. I mean, now this is the problem. You can deepfake any voice now with trivially, with local models, AI can impersonate trusted individuals trivially. Actually, Doppel does voice call simulations. It will help train your employees not to fall for this stuff. They did this with voice call simulation deployments. The targeted users in Doppel's own tests, on average spent six minutes conversing with a deep fake. And afterwards when they said, well, did you believe that that Was your boss? 100%. 100% believed the AI was human. If you heard that recording of me, you would think, that's me. I thought it was me. Doppel is the AI native social engineering defense platform. Doppel strengthens human risk management by training employees to recognize deception. While Doppel's digital risk protection detects and disrupts attacks across every channel, attackers are turning increasingly to AI to power more and more sophisticated strikes. You need something equally sophisticated. Doppel's using AI to fight back. With automated takedowns, multichannel coverage and AI defenses that build intelligence with every fight. Doppel works relentlessly to protect people, brands and trust. Doppel offers best in class integrations and partnerships to seamlessly integrate into your existing security stack. And Doppel's got the industry awards and the testimonials to prove it. Doppel recognized as a winner 2026 G2 leader in users most likely to recommend and Momentum leader and best support Join hundreds of companies already using Doppel to protect their brand and people from social engineering attacks. Doppel outpacing what's next in social engineering? Learn more at D O p p e l.com d o p e l doppel.com obviously you need this now. Thank you, Doppel for supporting security. Now that, that recording, every time I hear it just blows me away. It's just too dang good.

[Steve Gibson]

And the way things are going, if it was done again today, it would be even better. Dramatically better.

[Leo Laporte]

Well, one of the things that's changed is you can converse with it. And these new models, you can interrupt them. It's so natural, the flow is so natural that it sounds like a real conversation. It's amazing what they can.

[Steve Gibson]

Laurie had a conversation with some service person. Well, I mean, service bottom verbally on the phone went back and forth until they'd got enough done to realize, okay, I need to talk to a human. But it was like the future.

[Leo Laporte]

I mean, here we are. You don't know. Yeah. Picture of the week time, Mr. G. I will. I have not looked. I am a husband.

[Steve Gibson]

So I. Go ahead. I. I gave this picture the caption too much paint was being returned by well intentioned husbands.

[Leo Laporte]

And it is. I see a True Value hardware store sign.

[Steve Gibson]

Yes,

[Leo Laporte]

This I know from actual experience. And I bet you do too.

[Steve Gibson]

Tell us we're in somewhere. Where? This is a. Somewhere in a place called Healy is a True Value hardware store. And they've got one of those signs where they use the plastic letters that they stick on in order to, you know, like, you know, happy Father's Day or you know, yay, 250 years for the U.S. anyway, this one says Men choosing paint must have note from wife.

[Leo Laporte]

So I'm sure it's just a joke. I'm sure they're not serious.

[Steve Gibson]

I think that's probably true, but it makes a point that all of, all of us, all of we all know, married. Yes, it is true.

[Leo Laporte]

You're lucky because your, your walls, your new walls are all painted white.

[Steve Gibson]

White. No. But as every husband knows, Sundance, yes,

[Leo Laporte]

white is not white. There is eggshell white. There's a crew. There's white with a little gray in it. I don't know what that's called. That's really white.

[Steve Gibson]

Yes.

[Leo Laporte]

I don't know if this happened to you, but whenever the contractors, and we've had many come to our door and I open it, they say, is Lisa here? Same thing, same reason.

[Steve Gibson]

Well, and our contractors just this morning had this experience where we had some previous cabinets that wanted to be mounted in the garage. And I said, okay, put them in the back corner. And so they started to, you know, screw them into the back corner. Laurie came out and said, oh, that's all wrong.

[Leo Laporte]

Oh, God. Okay. That's why they always say, we've been

[Steve Gibson]

saying it's gonna be in the corner. Honey. No, no, I got stuff that has to go to the left of those. So they have to come out about a foot. And the, the workers kind of look at me and they look at her and I go, she's the boss. So, yes, Lisa and I had this

[Leo Laporte]

debate because they call me El Jefe. And I say, well, and they call you La Patrona. I said, doesn't El Jefe outrank La Patrona? She says, no. La Patrona is the highest rank. That's the four star general of the job. All right, what are we talking about today on stage?

[Steve Gibson]

Okay, so I've been seeing more and more of the non technical popular press beginning to rouse to the idea that AI is not just about chatting with an agreeable buddy, but that is. It is also enabling a new, darker side. And this has, of course, been something we've already spent some significant time looking at. But I wanted to share a sample of what the non security focused press is saying. One week ago, the publication the Atlantic. Oh, I thought I mis remembered that. I thought it was the Wall Street Journal. But anyway, the Atlantic, they ripped the band aid off this with their headline, assume you will be hacked. Which was then followed.

[Leo Laporte]

Yeah, that's terrifying.

[Steve Gibson]

Followed by the. Yeah, it's like, oh, hey, everybody, just give up. Just step away from your phone or your computer. They followed with the tease AI is enabling a deluge of. Of cyber attacks the likes of which we've never seen before. And of course, apparently the NSA would agree with them and. And that position.

[Leo Laporte]

Yeah.

[Steve Gibson]

So the.

[Leo Laporte]

Yeah.

[Steve Gibson]

The author of this wrote late last month. Oh, and he's writing in the first person. He said, late last month, I began to consider withdrawing some money from my savings account to buy gold. Whoa. He says it's the first time I've ever thought about panic buying. For all the firewalls and two factor authentication codes, the safety of the Internet is starting to falter. Hackers are gaining the upper hand over organizations around the world. Hospitals, energy grids, government agencies, and yes, banks, as AI tools, have become extremely good at writing code. They've also become extremely good at pulling off cyber attacks. He says Malware, after all, is still software. The reason has been a change in the scale, speed, and sophistication of hacks. That's difficult to overstate. Among its tens of thousands of clients, the cybersecurity firm Palo Alto Networks identified a fourfold increase in daily attacks from 2024 to 2025. Hackers are developing AI enhanced computer viruses that adapt on the fly to avoid detection. They're automating cyber espionage campaigns on foreign governments. They're stealing data in minutes instead of hours. And Leo, none other than Alex Stamos, he writes, a former chief security officer of Yahoo and Facebook, told me, quote, there's a crazy amount of offensive activity happening right now. Companies are getting hacked every single day. Yeah, yeah, I'll pause to note that. You know, everybody knows my position on this, right? My feeling is these are the chickens that are finally coming home to roost. Yes, massively wealthy companies such as Microsoft and Cisco have been far more focused upon adding new features which obsolete their current products, rather than investing in the security of their current offerings. You know, it's like, oh, we're sorry we're no longer offering support for the equipment we previously sold you and profited from. And just to verify how big a sucker you are, we suggest you do that again. Look at this shiny new product that pretty much does the same job as the old one, which now, sadly, oh, boohoo. Is no longer secure. Right. I have very little sympathy for mega corporations who rely upon the charity of other researchers to find the flaws that should never have shipped in their products to begin with. They've all been, you know, quite willing to ship flawed products and just hope for the best. Since all of this Internet Internet stuff began, the industry has limped along, existing in a state of precarious balance. And now AI is indeed threatening to rock that world by upstate by upsetting that status quo. So the Atlantic continues and oh boy, are they singing my tune. They wrote. If the NSA is perturbed by the rise in cyber attacks, which it apparently is, then surely my savings he's talking about in the bank are vulnerable. There could be any number of weaknesses in my bank's IT systems to directly hack. Or perhaps an AI written phishing email targeted at an employee, personalized to sound like a family member or manager could let hackers into the bank and empty my coffers. Even if the bank has great cybersecurity. An attack on another business a medical clinic I visit, a car rental company, a newsletter subscription could steal my payment information and potentially much more. The attack angles are seemingly infinite, and no one is adequately prepared. Adequately prepared. The term software engineering has always been an insult to the level of rigor demanded of mechanical, Civic and other engineers. Computer programs can be riddled with vulnerabilities and run just fine for years or decades, as much of the software underlying the web has done just that. Stamos, who's now the chief security officer at the AI coding company Corridor, said, quote, we've just been writing software in a totally slap dash and insecure way for decades now. With some small high stakes exceptions, such as software used on the International Space Station or nuclear submarines, code is written and deployed without much rigorous testing. If a bug is reported, okay, it gets patched. Such a relaxed security posture has been more or less fine because discovering vulnerabilities is difficult and skilled hackers are few in number. Either nobody found the bugs or nobody was able to exploit them. But traditional cybersecurity methods don't cut it anymore. Before you might scramble for a week to patch a hole, Giovanni Vigna, a cybersecurity expert at UC Santa Barbara, told me, quote, now you could have hundreds of those every week, unquote. Moody's Ratings has found that the time attackers take to exploit a publicly known vulnerability the digital equivalent of a robber plotting how to get around a bank's guards and cameras after obtaining a key fell from more than 700 days in 2020 to just 44 in 2025, faster than the average time cybersecurity teams take to make to to patch the bug. Governments and major companies are on high alert for AI enabled cyber warfare. The wake up call came this spring with the announcement of two extremely advanced cyber models. We all know where this is going, right? Claude Mythos Preview from Anthropic and the analogous GPT 5.5 cyber from OpenAI soon after. Many independent cybersecurity experts have told me, he writes, that these models are as or nearly as skilled as elite human hackers, which is why Anthropic and OpenAI did not release them publicly. Instead, the AI labs have granted a small number of partner organizations and government agencies exclusive access to the unrestricted versions of these cyber models in the hopes of shoring up their IT systems. And I guess now the NSA we know is among those. And yeah, let's hope the NSA tightens things up. And this month, he writes, Donald Trump signed an executive order to expedite just that. That is the shoring up of IT within government. Using these models, organizations can guard against the coming deluge of AI enabled hacks, most notably by using AI to detect and resolve vulnerabilities before cyber criminals could exploit them. Anthropic has itself used Claude Mythos Preview to find thousands of bugs in open source software packages, many of which went undetected for years or decades that undergird much of the Internet. Mozilla used Mythos to fix more than 400 bugs in the Firefox web browser in April, roughly 20 times more than it fixes in a typical month. And having an AI agent monitoring for intruders 24,7 could be far more effective than periodic cybersecurity audits. If you've been noticing more frequent updates in your web browser work Software smartphone apps it might well be because software companies are now using AI to scan their software for bugs. But if anything, these efforts are late. Even though they're not as powerful as Mythos, plenty of free and open source AI hacking tools are allowing criminals with little technical expertise to marshal the equivalent of an army of hackers at their fingertips. Tools from Google, Anthropic and OpenAI have guardrails in intended to prevent them from being used for hacks. But they're not perfect. All three companies have reported more and more sophisticated hacking attempts using their AI models. When the Courseware Canvas was attacked last month, upending classrooms in thousands of schools and universities worldwide, AI likely played a role and the criminal group responsible. A notorious hacking ring called Shiny Hunters is known for using AI in all sorts of scams. Just weeks later, Google Cyber Security researchers reported that Shiny Hunters had hacked into an Oracle HR system and may have stolen data from more than 100 organizations. Meanwhile, the Trump administration has forced Anthropic to revoke all public access to the latest version of Mythos, taking away perhaps the most powerful cyber defense tool we have from both the government and private sector. That does not mean you should withdraw your life savings and buy gold, but a tremendous amount of change needs to happen in a very short period of time. Open source AI models will soon catch up to mythos and GPT 5.5. The Internet needs upgrades at quote at a Y2K like scale unquote, rafi Kakorian, the chief technology officer at Mozilla, told me, referring to a widespread fear that computer programs interpreting the digits 00 to mean the year 1900 rather than 2000 would bring down the web. Of course, Y2K but I t professionals spent years preparing for and ultimately avoiding a Y2K apocalypse, he said. With AI we have months. No one company or government can demand the requisite collective action rapidly enough to complete completely secure our digital infrastructure, Wendy Whitmore, the chief security intelligence officer at Palo Alto Networks, told me, quote, there's no way organizations across the globe are going to patch everything that needs to occur within the next three to five months. At the same time that bots are making hackers more capable, the technology is also making the web less robust to attacks. Coding agents, due to their propensity to hallucinate frequently write insecure code, and humans in the thrall of vibe coding usually don't take the time to verify it. Spotty AI code has, for instance, reportedly caused multiple outages in Amazon's E commerce services. Meanwhile, the AI models being integrated across the web and into Amazon, Google, your bank's customer service department and more are themselves new, untested and vulnerable to all manner of creative attacks that allow hackers to request passwords and personal information. A few weeks ago, a group of cybercriminals basically just asked Meta's customer service AI to give them access to some 30,000 Instagram accounts, including the Sephora corporate account and the defunct Obama White House account. And the AI obliged. Some of our internal back end checks failed in this instance, but it wasn't due to the AI agent itself and we've addressed the underlying cause, wrote Andy Stone. A Meta spokesperson told me. The near future, he writes, is very likely to involve more frequent and more severe outages and hacks, just like those affecting Canvas, Meta and Amazon. Vigna said we will see more of these disruptions. I think it's inevitable in the short term. Smaller but crucial companies and organizations that are not web native think power plants, municipal government agencies, credit unions are especially vulnerable. They may be running all sorts of clunky legacy code and lack the IT capacity or the financial resources to make the necessary upgrades. In many cases, the person who wrote the bulk of an organization's software might be retired or dead. Take hospitals, many of which are already struggling to combat data breaches and ransomware attacks. Hospital IT systems are full of valuable data, health and financial data, and the incentive to pay a ransom is high when patients lives are on the line. Quote it's not a matter of will to increase it's not a matter of will to increase cybersecurity for hospitals, john Riggy, the national advisor for cybersecurity and risk for the American Hospital association, told me. It's a matter of resources and capabilities. AI, he said, will make everything worse, and the greater burden is always on the side of the defense. Missing just a single vulnerability can permit a catastrophic attack. An anthropic person told me that, Quote Hospitals, utilities and smaller banks run on software built by others, which Mythos is helping secure. Software upstream protects the organizations downstream that don't have the resources to staff their own security research team. Mozilla's Kakorian said Quote A worst case scenario over the next year or so might look like blackouts across the United States, telecommunications companies being hacked or our banking systems dealing with people losing money left and right. Every cybersecurity expert I writes this person spoke with for this story concurred. The next few months, couple of years or even longer is going to be rough, whitmore said. I hope it's not a catastrophic outage, but I'm concerned that 2026 really could be the year that we see some sort of attack like that become very successful. Anthropic estimates that a major cyber attack on just one of its 200 or so partner organizations could affect at least 100 million people. Collective action aside, some precautions exist that individuals can take short of liquidating into gold. Many of them are basic okay Use a password manager that auto generates long passwords, keeping software updated, restarting devices to wipe viruses from their short term ram. Be extra wary of all sorts of phishing, text and other low level scams. And you might consider simplifying your digital life by switching to a Chromebook, certain tablets or another gadget that is a thin client, meaning that very little software and data are stored on the device. Finally, even in the most catastrophic scenarios, perhaps we can ride out the AI hacks. No one knows just how many bugs are out there. If there's a limited pool of vulnerabilities online, things will settle down once they're all found, whether by hackers or security audits. But stamos said it's also possible that every time the top AI models reach a new threshold of capabilities, they discover a new pool of still more complex hacks. And so the chaos begins anew. So I think that the truest thing anyone can say at this point is that we have no idea what's going to happen. But I wanted to share that to remind everyone that was in the Atlantic, not some security magazine, not some podcast, some, some security focused podcast. Our listeners know that everything I just read we've all shared on this podcast, right? There was nothing new here. Even the, the expectations and the sentiments and the understanding of, of the balance of, of good versus malicious, all of that is like, yeah, we all know that. But this is now surfacing in stuff that other non techies read. So this understanding of what's going on, this awareness is, is now moving out into the mainstream. So you know, when a hurricane scale storm is heading toward Florida, nobody knows exactly what the consequences will be because storms are chaotic and unpredictable. We just have a sense of like, oh, this is a big one. So what's happening with AI is analogous. We know without doubt that we have filled the world with insecure software. Stamos said the same thing. And we know that a large language model AI is able to find many of the problems that have remained hidden in some cases for decades. Basically, it's about economics, right? We're not spending the money because these are hard things to find. AI makes them easier to find. So whose AI will be the first to discover a previously unknown problem? The good guys or the bad guys? And even if it's the good guys, remember that there. And this is one thing that this guy did not note that we know about here on the podcast. The reality is that discovering the problem is, as formally phrased in the fields of logic or philosophy, it's necessary but not sufficient. You cannot fix a problem you don't know about, so knowing about it is necessary. But the goal is to remove the existing defective software from the field, and only doing that is sufficient. As I've noted before, Patch Tuesday is no longer a Microsoft only occurrence, right? Other companies have developed automatic software deployment systems, but the vast majority of buggy software that's currently deployed in the field is never updated. So even if publishers obtain new and improved AI enhanced AI debugged software, the sufficient portion of the equation will remain unmet. Necessary, but not sufficient. If you fix the bugs but don't get them out into the field. I've noted how fortunate it is that all modern web browsers which present our personal machines largest and most exposed attack surface long ago incorporated asynchronous self updating technology. Thank goodness for that. And this leads us to our next interesting question, which we will get to Leo after you chime in and we talk about a sponsor.

[Leo Laporte]

You know, I would quibble a little bit with Matteo Wong, who wrote this piece in the article. First of all, if you buy gold, maybe if you store it in your house, you're okay. But most likely when you buy gold, you buy it, it's no different than anything else. You're going to store it in some account somewhere and it's just as hackable as anything else. So I don't think buying gold is the solution. Growing your own food may be the solution, but not buying gold. The other thing is, and I wish this, you see this all the time. He kind of conflates the, the vulnerabilities we see with AI vibe coding, which is not really the case. That's not the problem here. The problem is we well know on

[Steve Gibson]

this show as humans is years of lazy programming.

[Leo Laporte]

And the Instagram case is a perfectly good example. It wasn't the helpful AI customer service agent that was the problem was. The problem is that Instagram didn't require a second factor of proof and that was their, their policy, not the AI's policy. So stop. And even Instagram told him it's not the AI dude. But he, he wanted to believe it. And I think this is the part of some of the problem we have with AI's reputation these days.

[Steve Gibson]

People blame it and, and oh, although I did just see Leo, there was a, I can't remember now who, who did the survey. Chatbot use has now passed 50%.

[Leo Laporte]

Yeah, everybody uses population, everybody. I also saw surveys that only 18% of people trust the answers it gets from AI driven search. So you know, they may use it, but they don't trust it. The other thing, you know, it's important to point out that AI is going to be in some regards, as you, as we've said on this show, this is the solution here. Yes, bad guys use AI, but AI is also, I mean, look, and you're going to talk about this in just a bit, I mean, finding these problems and fixing them, problems humans cause, not, not AI. So yeah, you know, but you know, this is, as you point out, this is mainstream press. This is what real people read and, and see.

[Steve Gibson]

And yeah, yeah, it's hard to go wrong. It's hard to go wrong quoting Stamos since he certainly knows he called the

[Leo Laporte]

right people, I must say.

[Steve Gibson]

Yeah, yeah.

[Leo Laporte]

As you know, Alex was a guest on our show last Wednesday on Intelligent Machines. I love. I love Alex Stamos. This episode of Security now brought to you by Trusted Tech. Do you hear that? Listen. No, I don't hear it. But I think if you're an IT professional, you probably should hear the clock ticking because July 1 is just around the corner. It's a week away. If you're managing Microsoft 365 for your company, you, my friend, you lucky guy, you're responsible for both the cost and whether it's set up correctly. And in about eight days on July 1, as we record this, Microsoft is raising prices. And they warned you. They've been warning you for months. But what that means is any mistakes in your licensing are about to get more expensive. It's not your fault at all. Most Companies using Microsoft 365 are in one of two situations. They're either over licensed, which means they're paying for unused seats and features, or they're under licensed, which creates compliance and security risks. And sometimes it's even both. Like one department has too much and one department has too little. The result? Well, either wasting thousands, sometimes tens of thousands of dollars per year on tools your team doesn't use, or. Or worse, missing critical security features you thought you had. Trusted Tech helps businesses understand what they have, what they actually need, and how to lock in the right setup now before the costs go up. Eight days from now, July 1, Trusted Tech's team ensures your M365 environment is well supported and aligned with how your business actually operates. They're the experts in this. Oh, and that's not all they do. If you need ongoing help, they're great for support, too. They offer reactive support for your Microsoft environment through their certified support services. But right now, since this is so urgent, let's talk about Microsoft licensing. It isn't your fault. It's constantly changing. It's confusing as heck. You got your E3, your E5, you got your business Premium, you got your add ons, you got that new E7. It's confusing and it's easy to misconfigure and overpay. And I should remind you, licensing mistakes don't just cost money. They can create compliance exposure. And either way, it's going to get more expensive after July 1st. So even if you think your licensing is dialed in, it's probably worth a second look. Listen to what Kevin Turner, you know his name, former Microsoft coo, says he was talking to Trusted Tech. And he said this quote, you have an incredible customer reputation. You have to earn that every single day. The relentless focus you guys have on taking care of customers gives them value and differentiates you in the marketplace. You could tell he has a little soft spot for Trusted Tech. So do I. And you should too. Because after July 1st folks, you're stuck paying more. And this is your last chance to fix your licensing before costs go up. Trusted Tech is offering a free Microsoft 365 licensing consultation right now. Visit TrustedTech Team,/SecurityNow 365 and get a clear data backed view of your current licenses, what you're wasting, and how to lock in savings before the price increase. Go to TrustedTech Team SecurityNow365 and submit a form to get in contact with Trusted Tech's Microsoft licensing engineers. You owe it to yourself. You owe it to your company. TrustedTech Team SecurityNow 365 and if I were you, I'd do it right now. Don't wait. TrustedTech Team SecurityNow365 now back to security now. Now you were saying that this self updating technology in browsers is really a good idea.

[Steve Gibson]

Thank goodness we have that in place. Yes, because that's been there for a long time. Because even pre AI we recognized that the browser was being attacked. It represent the largest exposed attack surface that we have. As we know, when you go somewhere the browser is receiving JavaScript code which by design it runs like from some random foreign site that you have no, you know, reason to believe is not malicious and so there's danger. So okay, I got a kick out of the email from a listener of ours named Joey Albert who said he started out his note saying looks like Mythos needs to run a few more times on Firefox. And that was followed in Joey's note by a link to a piece in Cybersecurity News from last Thursday which carried the headline Multiple vulnerabilities in Firefox 152 enable remote code Execution Attacks. Whoopsie. We thought Firefox was fixed. Joey, of course, is referring to the fact that Microsoft was among the handful of companies to receive that early access to access to Claude Mythos Preview. And as we reported using Mythos, Mozilla did indeed. In fact, the previous article in the Atlantic referred to the 400 bugs that were fixed, you know, 20 times more than was normal for, for the same type of cycle once they were all gone, which is to say once Mythos could find no additional problems, Firefox was presumed to be all fixed, right? It's like, okay, we found them all, but if so, where did all these newly discovered problems come from? So before I proceed to enumerate the changes in 152, which is now the current release, as I'm as I was writing this, I want to share what cybersecurity News had to say. So they wrote Mozilla has released Firefox 152 to address multiple high severity vulnerabilities that could allow remote code execution and sandbox escape attacks. The security Advisory published on June 16 highlights a wide range of flaws affecting core browser components and emphasizes the urgency for users to update immediately. Okay, well technically that's true, but as we know user thank goodness users don't need to do anything or it would be a disaster. The next time they launch their browser it will auto update. You know. So that's taken care of. The article continues writing Several of the patched vulnerabilities are classified now. These are again new vulnerabilities that Mythos missed the first time around. Classified as high impact, primarily involving memory safety issues, use after free bugs, and privilege escalation flaws. You know, the usual suspects. In other words, these vulnerabilities can be exploited by attackers through specially crafted web content, potentially allowing arbitrary code execution on affected systems. Notable high risk vulnerabilities include so we have a bunch of 2026 CVEs, so I'll leave off that preamble. We have 12289 a privilege escalation flaw in the web render component that could allow attackers to gain elevated access 12291 a use after free vulnerability in the HTTP networking component oops leading to memory corruption 122.93 a use after free issue in the web GPU component that could be leveraged for code execution. 12294-97 so 94, 95, 96, 97 multiple sandbox escape vulnerabilities impacting DOM workers, document object model workers, navigation and process sandboxing mechanisms 12299 a JIT, you know, just in time miscompilation bug in DOM and HTML components that could result in unpredictable execution behavior. And additionally, Microsoft reported several memory safety bugs 1-229-098-12326 and 12328 that demonstrated memory corruption. They write. Such flaws are particularly dangerous because attackers can exploit them to execute arbitrary code remotely. The presence of multiple sandbox escape vulnerabilities significantly increases the attack surface. In a typical exploit chain, an attacker may first exploit a memory corruption flaw to gain code execution within the browser. Then use a sandbox escape vulnerability to break out of the browser's security boundaries and compromise the underlying system. For example, combining 12291, which is a use after free with 12294 the Sandbox Escape in DOM workers could enable a full browser to system compromise, which you know in practical terms means you go somewhere and your system is taken over. I mean, you've got bad code running in your machine just by visiting a website, they wrote. In addition to high risk flaws, Mozilla addressed several moderate and low severity vulnerabilities, including the same origin policy bypass 12304 affecting cookie handling information disclosure issues in web GPU and password manager components multiple mitigation bypass vulnerabilities in DOM security mechanisms Denial of service issues meaning something crashes in media playback and graphics components numerous memory safety bugs across various modules. While these issues are less severe individually, they can still be chained with other vulnerabilities to enhance attack effectiveness. According to Mozilla's advisory, these vulnerabilities have all been patched in Firefox 152, Firefox ESR 1.4.0.12 and ESR, which is the one I'm using 11537 because I'm still running that on my Windows machine, Windows 7 machine. Oh, and they also fix these things in Thunderbird 152 because of course when you're viewing a a an email that is HTML, it's also able to be basically a browser window. So the article concludes, users and organizations should update to Firefox 152 or later. Again, you don't have to do anything unless you turned it off for some reason. Apply the latest ESR updates Enable automatic updates Monitor systems for signs of suspicious browser activity or exploitation attempts. The Firefox 152 update addresses a critical set of vulnerabilities, many of which could be chained to achieve remote code execution a full system compromise. Given the presence of active exploit primitives such as memory corruption and sandbox escapes, timely patching is necessary for maintaining browser security and again don't have to do anything. So I was curious to see whether anything was indicated about where these new very arguably very bad vulnerabilities came from. So I checked out the advisory in detail. What I discovered was that the totals the the the the total problems were 13 with it had a high impact rating, 18 were moderate and 9 was low impact. And most interestingly, Mozilla credited a wide range of human researchers for their responsible reporting of these discoveries. Two of the researchers discovered and reported two vulnerabilities each, while everybody else reported one. So there was lots of security research input. And the researchers appear to be internationally spread with names that suggest origins in Korea, China, Vietnam, Japan and the Arabian Gulf. So how do we rationalize or how are we to understand Mythos missing these? I think there are a number of things going on. For one thing, remember that LLMs are still non deterministic. That temperature that we talked about way back in the beginning of all of this deliberately introduces some entropy, some uncertainty into LLM output by mixing a controllable amount of that of that derived entropy into the neural network nodes. So it might be exactly as our listener Joey Albert suggested when he wrote looks like Mythos needs to run a few more times on Firefox. I would not be at all surprised to see another run of Mythos finding things that it didn't see the first time. And yeah, infuriating as that might be, the output from this technology does have a random factor that will vary the model's output. Ask the same prompt again, you get a slightly different answer. So slightly different. Looking in detail for software flaws is going to catch some and maybe miss some. But given the diversity of discoverers who are discovering many serious flaws that have never been found before and that we're seeing that no one is has any particular secret sauce meaning that Mythos, while yes powerful, is not particularly unique. I fully expect that these other researchers are pouring over Firefox's open source code through their own vulnerability, discovering LLM systems. I would imagine while these were provided to Mozilla by humans, that they had an AI in the closet that was, you know, helping them make this possible. The one exception I would make to the, and this is referring to what I said before, the no one has any particular secret sauce notion is I really believe that Microsoft with their accursedly named codename EM dash system, probably I think it is special given what we know of it versus all the others. I think there's a very real likelihood that Microsoft has created something that significantly blows away any of the more generic vulnerability discovery systems. You know, they weren't trying as we know, Mythos was a general purpose AI, meaning that you can ask it about the fall of the Roman Empire and get results. Codename M dash is, you know, a lash up. It is model agnostic, so you can plug different models into it. But you know, they've, they've developed a very sophisticated system that, you know, anthropic is not Talking in detail about how, how the Mythos preview operates, but it just doesn't seem to me, it seems to me like they're going back based on raw brute strength model power rather than on really finessing what you, the way you ask the model to do its work. So why would any one system find something that another one did not? Well, we know how, how tuned large language models are to the way you ask the question. A lot of these jailbreaks are, are just phrasing what you want in a different way, sometimes in a surprising way, and the model gets surprised into answering you. So I think it's a combination of the effects of this LLM model temperature, different model training in detail, and difference in the specific prompting that the differing models are given. In other words, the use of LLMs for software Vulnerability discovery is still very new and there are still a great many variables that can affect its results. So I think that's probably what we're seeing.

[Leo Laporte]

You know, it's unclear whether Mythos is still running, whether Project Glasswing is still going or not. Right.

[Steve Gibson]

Or it had to be completely withdrawn even from the private partners.

[Leo Laporte]

Right.

[Steve Gibson]

You have to imagine that the administration still has access to it.

[Leo Laporte]

Well, it's so confusing. When Trump was at the G7 summit, he met with Dario Amodei, the CEO of Anthropic, and apparently was somewhat appeased and said, yeah, no, I like Anthropic now. I like Mythos, but I still don't see a change in the ban. It's very confusing. It's just very confusing. The good news is it's given everybody the incentive to take a look at other models. And there's, you know, there's even some.

[Steve Gibson]

There are other. Yes.

[Leo Laporte]

That are very good. So. Yes, it's just a matter of time. I mean, it's happening so fast now. So fast.

[Steve Gibson]

Yeah. Okay, so let's take one more break because I, I, I want to kind of space these out, but we're going to talk about Rogue Planet, which is the name of another problem, and you. And unfortunately, you know, who gives these things their great names?

[Leo Laporte]

Who?

[Steve Gibson]

Nightmare Eclipse.

[Leo Laporte]

Oh, he's obviously a fan of the famous klatu Barada nikto. Forbidden Planet, Right? Yeah, that's right. Is that, Am I right? Is that where that's from? I don't know.

[Steve Gibson]

No, that's the day the world was.

[Leo Laporte]

Day the world stood still. Right. What's Forbidden Planet? That was.

[Steve Gibson]

Robbie Rotu was the name of that super powerful robot, and that was the

[Leo Laporte]

message that you were supposed to give

[Steve Gibson]

Klaatu to so that it would not destroy the Earth.

[Leo Laporte]

Yes, yes.

[Steve Gibson]

Please do not. Please do not destroy the Earth today.

[Leo Laporte]

You know kids, this is just something you got to look forward to when you get into your 70s. The things you remember are complete. Talk about probabilistic.

[Steve Gibson]

You don't know what you ate last night for dinner, but boy, do you remember.

[Leo Laporte]

Klato barekto necto barada nikto necto. Yeah. Isn't that weird? Well, I just thought if ever I need to save the world, it's important that I remember that much.

[Steve Gibson]

Absolutely.

[Leo Laporte]

Maybe if you want to save your company, it's important that you remember the name. Expo, our sponsor for this segment of security now. Xbow. Like bow and arrow, Xbow, you probably do know the name. These are, this is probably one of the best known pen testing firms out there. And you may be happy to know that they have embraced AI. AI is, as we've been talking about, change the pace of everything from how software gets developed to how it gets attacked. Engineering teams are moving fast now, faster than ever, creating more and more applications. The problem is, you know, real security just can't keep up. Pen testing is still one of the most trusted ways to understand real exploitable risk. I mean if you ask somebody, you know, how should I, how can I protect myself? The best you'd say, bring in some pen testers, really challenge your security stance. But in an AI driven world, pen testing can become a bottleneck. Security teams are forced to choose between slowing down development, we're moving here just to stay secure, or moving fast and accepting gaps in coverage. Well, I should correct that. That's how it used to be. Expo eliminates that trade off. Xbow Expo is an autonomous offensive. Oh, I love these words. Let me say it slowly so you can get it. Autonomous offensive security platform. Autonomous. It runs continuous AI driven pen testing, mirroring real world attacks. Doing it really, really well. Expo doesn't just scan for vulnerabilities. It discovers exploits and validates them. So you're only dealing with issues that, that actually matter. That means dramatically fewer false positives and a clear view into real attack paths. This is why we love pen testing with but Expo makes, you know, puts its pens testing on steroids. It tests run in hours, not in weeks. You get complete visibility into how an attacker would move through your systems and the ability to uncover issues that traditional tools just miss, including zero days, novel attack paths and expose results speak for themselves. Application security lead AT says Nam CZ says, and this is a quote, quote even Right now after one year, I don't know any other company that is at least close to Expo in terms of agentic pen testing. End quote. In fact, if you know the name Expo, it's probably because of agentic pen testing. They've really the pioneers of this. The result? Predictable cost, consistent quality, and most importantly, stronger security without slowing down your engineers. Expo helps security teams keep pace with innovation and cover more apps more often with the resources they already have. Founded by the team behind Microsoft Copilot and already trusted by companies ranging from fast growing startups to Fortune 500 enterprises, Expo is quickly becoming a mission critical layer in modern security stacks. Go to Xbow.com to start a pen test today. Expo.com Expo I thank them so much for their support of security. Now expo.com and now back to Steve

[Steve Gibson]

so when I first saw that Rogue Planet was the name given to a newly discovered zero day for Windows, my first thought was that sure sounds like the naming favored by the hacker Nightmare Eclipse. And as it turns out, yes indeed. Last Wednesday, Bleeping Computer covered the story under their headline Microsoft Working on Defender Patch for Rogue Planet. Zero Day and Bleeping Computer wrote, Microsoft confirmed that it's working on a security patch for a Defender zero day vulnerability named Rogue Planet, disclosed one week ago. Now one week ago was Patch Tuesday, which and so of course these are strategically timed, right? The security researcher who published a Rogue Planet exploit during the June 2026 Patch Tuesday, known as Nightmare Eclipse, said it affects fully patched Windows 10 and Windows 11 devices and allows attackers to spawn command prompts or with system privileges via a Microsoft Defender race condition. He shared a proof of concept exploit in a self hosted Git repository, claiming that Microsoft had previously targeted and removed their repos hosting exploits on GitHub and GitLab. Nightmare Eclipse said, quote, the exploit is a race condition, so it's a hit or miss. I've managed to get a 100% success rate on some machines or while it struggled to work on others. The proof of concept for Rogue Planet works regardless if real time protection is on or not. So he found some compromise in Microsoft Windows Defender, the article says. Microsoft spokesperson told Bleeping Computer when asked for a comment at the time, quote While Microsoft is aware of their reported vulnerability and is actively investigating the validity of and potential applicability of these claims, Microsoft is committed to investigating security issues and updating impacted products to protect customers as long as possible. Which you know. Micro Speak On Tuesday, Bleeping Computer writes, One week after the Rogue Planet flaw was disclosed Microsoft assigned it CVE506.56 to the Security flaw and confirmed it's currently working on a patch, but did not acknowledge that Nightmare Eclipse was the one who found the vulnerability. Right there I, you know New strategy Microsoft's advisory published last Tuesday said Microsoft is aware of an elevation of privilege in the Windows malware protection engine in Microsoft Defender, publicly referred to as Rogue Planet. We're working to provide a high quality security update that addresses this vulnerability. We'll provide information in this CVE when the update is available. The Rogue Planet release is part of an on rights believing computer. The Rogue Planet release is part of an ongoing dispute between Nightmare Eclipse and Microsoft over the latter's bug bounty and vulnerability disclosure practices. Of course we know none of the details. Over the past several months the researcher has publicly leaked multiple Windows zero day exploits, including for the Blue Hammer, Red Sun, Green Plasma, Mini Plasma, Yellow Key and Undefend flaws. Some of these zero days affect Microsoft Defender while others target BitLocker and Windows components. The company reacted to Nightmare Eclipse's disclosures by issuing warnings of legal action when people engage in, quote, malicious activity causing real harm to our customers. Unquote, right? Leading cybersecurity experts and researchers to believe that Microsoft was threatening the researcher. Microsoft fixed the Green Plasma, Mini Plasma and Yellow key flaws last week, they wrote last week as part of the June 2026 Patch Tuesday updates. So yes, Nightmare Eclipse is back at it again, dropping deliberately timed zero days on successive months patch Tuesdays. And if I recall, I think it was sometime in July that that Nightmare Eclipse had said oh baby, hold on, I've got a big one coming. So you can imagine Microsoft must be a little nervous up there in Redmond. So I mentioned at the top of the show an interesting database that had been discovered when I first heard the term fortibleed alongside everything now is, you know, bleed alongside bleeping computers headline for their coverage of the story which was fortableed Leak exposes Fortinet VPN credentials for 73,000 devices. My thought was that the popular Fortinet Fortigate VPN must have some critical vulnerability that caused it to bleed its authentication thus for to bleed. But that's not what was going on here and what is going on is worrisome in a new way. Bleepy Computer wrote the following they said a newly discovered data leak dubbed fortibleed has exposed what appears to be and it's been verified by good people. We'll see in a second to be a collection of Fortinet and Fortigate VPN credentials for 73,932. In other words, almost 74,000 firewall URLs at organizations worldwide. The exposed data was first discovered by security researcher Bob Dyachenko, who says he found a server containing he found a server containing what appeared to be valid Fortinet VPN credentials. You know, like in other words, a directory sitting somewhere open, including usernames, email addresses and plain text passwords. Yikes. Okay, so fortableed is not directly a vulnerability in any Fortinet product. Rather, it's the name given to the discovery of a significant repository of Fortinet VPN appliance credentials. So bleepy Computer continues writing According to screenshots and information shared by Dyachenko, the database contains entries for Chevron, Samsung, Foxconn, Comcast, AT T, Mercedes Benz, Toyota, Sinopec, State Grid and many others. Diachenko wrote on LinkedIn quote, Massive Fortinet Fortigate brute force active exploitation campaign uncovered in action. The he said thousands of top vendors instances are listed in the files. One File alone has 21,634 domain names from Chevron to Fortinet itself, all with potentially working passwords to the Fortigate appliances obtained through various means they wrote. The exposed data also includes comments listing each organization's industry, revenue and number of employees. Wow, that. I mean, could you imagine anything more perfect than a directory for deciding who to attack next? With a ransomware campaign, you've got the ability to log into their network and you know the or the industry they're in, how much money they make and how many people they've got. You couldn't ask for anything better for planning attacks. Dyachchenko later shared additional information that claimed the operation was conducted by a Russian speaking multi operator threat group that harvested credentials for Fortigate SSL VPN devices. Okay, so there's a different group that's harvesting credentials, but the harvested credentials are then being added to this growing database for purposes we don't know, bleeping computer said. According to Diachenko's investigation, the attackers allegedly conducted approximately 1.16 billion credential attempts against 320,777 FortiGate VPN appliance targets, and an additional 2.1 billion attempts against 163,650 Microsoft SQL Server systems. He further claimed the threat actors intercepted SSL VPN authentication hashes, cracked them using a 45 GPU cluster managed through Hashtopolis, and use the recovered credentials to move laterally into internal active directory environments. Yikes. This is the world we're in today. Diachenko told Bleeping Computer he obtained these details after after analyzing additional files inadvertently exposed on the same server, writing they accidentally left an open directory with artifacts, connection strings, tooling scripts and data online analytics obtained via their Cron jobs, bash histories logs and so forth. The researcher also stated that multiple organizations across Japan, Taiwan, Vietnam, Iraq and Turkey were fully compromised, including a Turkish NATO defense contractor from which classified documents were allegedly stolen. Wow. The threat intelligence company Hudson Rock has since published its own analysis of the exposed data. After receiving the data set from Dyachenko, the company described the collection as one of the largest known troves of compromised Fortinet related credentials. According to Hudson Rock, the Data set contains 73,932 unique firewall URLs across 194 countries, impacting 21,632 unique domains. The company says the attackers maintained detailed logs of successful compromises and assembled a database containing verified credentials for organizations across nearly every major industry sector. Again, verified credentials among the organizations Hudson Rock says appear in the data set are Foxconn, Samsung, comcast, Siemens, Lenovo, PwC, Accenture, Oracle, and numerous government agencies and critical information and infrastructure operators. So, okay, so let's just stop for a moment to consider what this means. When a bad guy manages to log into a typical network border device, they may be able to arrange to be its manager, but you know, what that actually gets them is uncertain. It can often lead just to a dead end. Okay, so I got into some appliance and I can pretend to be in charge, but I can't do anything else. By comparison, when a bad guy arranges to log into an enterprise's vpn, they're likely connected to an extension of the enterprise's internal network. I mean, that's why you log into an enterprise VPN is to get on its net as if you were there sitting in your office. You can, you know, be out of office and still have access to all the internal stuff. Well, so if a bad guy gets, you know, is able to do that, that's when their fun just gets started. While the best practice of rigorous least privilege, as we've discussed is possible, that is, you know, absolutely rigorous least privilege. It's also another example of the classic trade off between convenience and security. The default way of configuring a network is just to throw everyone on the same bus. Everything will work and the security aware IT guys will just be hoping for the best. The downside of this simple flat network organization is that every device on the network can see every other one. So when some cretin manages to log into the corporate vpn, they too can now see every other device across the enterprise's internal network, the entire network. The whole point that I want to make refers to that report of 1.16 billion credential attempts against 320,777 Fortigate VPN appliance targets and an additional 2.1 billion attempts against 163,650 Microsoft SQL Server systems. We learned from Diochenko's research that this was a pure and simple, widespread and disturbingly successful brute force attack which results in the compilation, or resulted in the compilation of a massive database of of extremely valuable enterprise VPN credentials. Never has there been a more compelling case to be made for the use of multifactor authentication. Yes, require a username and password, a complex password. Then require something else. Anything else that would prevent any simple brute force campaign from succeeding in the future. And by the end of today's podcast, we're going to see that a brute forcing campaign could really leverage a widespread proxy network to spread failed login attempts across a never repeating broad base of consumer IP addresses. Which is to say, one of the ways the bad guys are sidestepping both failed login attempt counters. In geofencing IP restrictions, we have seen an instance where a massively parallel multifactor authentication protection was breached because there was way too much latitude given in inputting previous and no longer technically valid, you know, six digit codes. Remembered that it was possible to, to submit too many tries in too short a time so that the, so that it was actually possible to breach that. But that was really a set of special cases and Microsoft, that was the, the victim and the target of that, fixed those, you know, that, that extreme latitude that made that possible. Okay, so what else was discovered about this disturbing authentication database? Bleeping Computer explained. The company also releases statistics showing that the highest number of affected devices was in India, the United States, Taiwan, Mexico, Turkey, Thailand, Colombia, Malaysia, Chile and the uae. The most common sectors for the listed companies are telecommunications, IT services, financial services, government organizations, healthcare providers, educational institutions and manufacturing. Okay, now I'm just going to say, I'll just note that given the nature of the attack, this does not indicate to me any targeting of those specific industrial sectors. What it does indicate is the demographics of Fortinet's users. Right? Those are the people who have these devices that are subject to compromise and whose authentication has been aggregated into this database. So Bleeping COMPUTER CONTINUES writing One strange aspect of the leak is that many of the exposed credentials were long, complex passwords that would ordinarily be considered difficult to crack. Cybersecurity researcher Kevin Beaumont, you know, Gossie the dog, independently reviewed portions of the exposed data and told Bleepy computer that some of the credentials are authentic. Beaumont said, quote, I've been able to confirm the authenticity of some of the admin logins and passwords. This looks like a real dump. Unquote. After further review of the data shared by Hudson Rock, Beaumont published additional findings indicating that the data set contains credentials for roughly 75,000 Fortinet devices, most of them which are currently and remain online. So that's just unbelievable. You know, just think of what this means. Around 75,000 public and private enterprise networks of any kind exposed to external intrusion. And here's a database of like this, all of them that you have access to. According to Beaumont, they wrote the data appears to have originated from X exported Fortinet configurations because it contains information including email addresses that is typical only, typically only accessible through configs. On the other hand, it seems to me once the bad guys or their automation, I'm sure they're automated, have cracked into the Fortigate vpn, those credentials can be exported from the vpn. So it doesn't seem that difficult to me if you're able to get in as a manager to export them. Bleeping wrote. He also said the affected IP addresses are different from those in last year's 2025 Belson Group Fortinet leak, further indicating that this is a more recent and larger collection of compromised devices. Beaumont and he verified that multiple organizations listed in the data set were using valid credentials and observed that many affected devices were running relatively recent Fortinet OS versions. Kevin wrote, quote, the data is legit. It's around 75K devices. Almost all are still online and Fortinet devices. It appears to be a recent. It appears to be recent data, wrote Kevin Beaumont. So, based on network data from Shodan Bowman, Beaumont says the leak contains approximately half of all Internet accessible Fortinet firewalls and said that a majority of the affected devices exposed their Fortinet. I'm hard. It's hard to even read this. Their Fortinet management interfaces directly to the Internet. It's like, God, you know, Fortinet, please, please don't make it easy to do this. It must be easy if half of them have done it. You, I mean, there's no way you've explained all the dangers to your users or they would just say no. What's the default? On or off are the half that not exposed, not not exposed because they turned it off. It's just. And if it's on, does everyone in the world need to have access to it? The source of the configuration data, says Bleeping Computer, remains unknown. With it unclear whether it was stolen through previously disclosed Fortinet vulnerabilities, a newly discovered flaw, or or another method. Neither Diachenko, Hudson Rock nor Beaumont have identified how the configuration data was originally obtained. Hudson Rock has created a free for to bleed lookup tool to check if your organization is impacted. Okay, so the only thing protecting any enterprise that's on the list is that if the bad well, if the bad guys may not yet have gotten around to them, right? You get you're a needle in a haystack with seven with nearly 74,000 other needles around you. Presumably if they haven't attacked your network yet, it's because they just. They're just. It's they're buried in riches. So I've got the link in the show note for anyone who's interested. It's HudsonRock h u d s o n r o c k.com/fortinet f o r T I n E t. You can go there to see if your organization is affected and wow, if you happen to know that you are a for to get a Fortinet user then don't hesitate. They said organizations in the data set should immediately rotate passwords. Yeah, no kidding. Associated with Fortinet VPN and admin interfaces, enforce multi factor authentication, examine gateway logs for suspicious activity, and monitor for exposed employee credentials. Bleeping Computer contacted Fortinet regarding the exposed data and will update this article if we receive a response. They conclude and in a follow up piece, Bleeping also reported that CISA had not surprisingly jumped on this and was urging everyone not to wait to make changes. Fix them immediately. Do this now, bleeping wrote. CISA also advised Fortinet customers, you know, within their reach, largely federal, to store admin credentials using the modern password based key derivation function pbkf2pbkdf2 hashing algorithm, and to restrict firewall management interfaces from public Internet access and remove any unauthorized accounts. Yeah, why not to reduce the attack surface as much as possible. So amen to all that advice. And wow, if you are again, if you're a user of Fortinet, you really need to immediately rotate your username and password. I would absolutely add two factor authentication Turn off any Internet facing management interface. Please first and foremost, as I also mentioned at the top, F5 has issued emergency updates to NGINX. NGINX is one of the major contemporary recently written web servers on the Internet. The security company F5 purchased the company behind Nginx seven years ago back in 2019 and has been maintaining the open source server ever since. So last Thursday, rather than waiting for NGINX's regular update cycle, F5 released emergency security updates to address multiple vulnerabilities, including two critical severity flaws that could allow attackers to execute code on vulnerable systems. F5 also released security fixes for multiple NGINX software products affected by these two vulnerabilities, including NGINX's plus and NGINX open source NGINX Gateway Fabric and NGINX's Instance Manager. Admins who cannot immediately install the security updates can mitigate one of the vulnerabilities by disabling HTTP 3, which is the QUIC version, you know quic, which establishes connections using UDP protocol rather than TCP in order to avoid the delay of the handshake which is otherwise part of TCP connection setup. Also, you can remove the ignore valid headers off directive, meaning pay attention to invalid headers and fail the the the query of the HTTP query and also reduce the large client header buffers directive size below 2 megabytes. F3 has also addressed two high severity NGINX Gateway Fabric Security flaws that can be exploited by authenticated attackers to inject arbitrary nginx configuration directives. And again, it's, you know, it's easy to run through that by exploited by authentic by. Oh, I'm sorry, exploited by authenticated attackers. So if they, if an attacker did get credentials then they would be able to to get up to some mischief. But that's been updated and foreclosed on. F5 did not indicate that any of these security issues have been exploited in attacks. But F5 vulnerabilities have often been exploited by cybercrime and nation state threat groups. In recent years, for instance, hackers have targeted security flaws in F5 products to breach corporate networks, deploy data wiping malware map internal servers, hijack those devices, and to steal sensitive documents from victims across the world. Last October, F5 disclosed that state baked baked State backed attackers had breached its systems the previous August and stole undisclosed big IP security vulnerabilities and source code. So over the past several years, CISA has flagged seven F5 vulnerabilities as being actively exploited, with four of them targeting targeted used in targeted ransomware attacks. And all of this matters because F5 is one of the serious networking players in the industry. They themselves are a Fortune 500 company. They provide cyber security, application, delivery network and various other services to over 23,000 customers worldwide, including 48 of the Fortune 50 companies. So 48 of the top 50 companies in the US and 80% of the global of the Fortune Global 500. So their hardware, this F5 hardware is the choice of the high end companies. Unfortunately it needs to be kept up to date. So let's hope those fixes make it out into the field quickly and thoroughly. Okay, so Leo, we're going to take a break and then I've got something so fun to share with our listeners. It's the guy is Will Kelly, a listener of ours who was bothered by the fact that he, he was having a problem not anthropomorphizing Claude. Yes, because it just seems so human.

[Leo Laporte]

It seems like a human. Yeah.

[Steve Gibson]

He went above and beyond what is possible. I'm going to share what, how he instructed Claude and then some samples of Claude's output after obeying these deeply personality modifying changes. I wasn't aware you could do this to your AI. Turns out you can. And I know that our list.

[Leo Laporte]

Oh, I might do it.

[Steve Gibson]

Believe me, I know you will.

[Leo Laporte]

Oh, I can't wait. Yeah, I spent a lot of wasted hours is customizing my agent to be, well frankly more interactive. So I think probably anything that can keep me from confusing it with an entity as opposed to a computer program would be helpful. I think we'll see though if you can cure me. I don't know. This episode of Security now is brought to you by Threat Locker. We love these guys. In fact, Steve and I are going to Vegas for Black Hat August. I think we're doing the show From Black Hat August 5th, I think on when On Wednesday. On a Wednesday. We're going to Flip Flop Windows Weekly and Security now will be at Black Hat at the Threat Locker booth. I hope you'll come by and see us. That's going to be a lot of fun and I think we'll probably do selfies and stuff after this and I

[Steve Gibson]

do get questions from listeners every year. Are you going to be at Black Hat in Vegas?

[Leo Laporte]

Have you ever gone?

[Steve Gibson]

No, never.

[Leo Laporte]

Neither have I. You know Father Robert goes to Black Hat and Defcon every year. Well, we have plenty of people there. We'll give you more details about that. But first let me tell you a little bit about our sponsor, Threat Locker. We love these guys. Threat Lockers. Steve and I were out at Orlando at The Zero Trust world actually earlier this year, Threat Locker, zero Trust platform, they exp. They expanded its capabilities. They announced this. I think they announced at zero trust rule, maybe at RSEC shortly thereafter. ThreatLocker now delivers the industry's most comprehensive suite of zero Trust solutions. So it's always had endpoint protection, but now company networks and the cloud are protected with zero trust. This is huge. By extending zero Trust enforcement to cloud services and company networks, ThreatLocker ensures that devices are validated through a secure broker before connecting to platforms. I'm talking all the SaaS platforms you use. Salesforce and Microsoft 365 Asana, we use Google Workspace, that's their GitHub. What this means is even if a user is successfully phished, and these days it's increasingly likely that one of your users will be successfully phished. It happened to us, actually. Even if they get phished attackers, this is hard to wrap my head around. This seems so good. Attackers cannot access those resources, cannot get into that workspace unless they'd actually. In order to do this, they'd have to have physical possession of the user's trusted device and get through whatever biometrics you've already put on that device. Windows, Hello. Or Fingerprint or whatever. I mean, in other words, impossible, right? Well, I should never say impossible, but a lot harder. Threat Locker works across all industries and provides 24.7us based support. It works on Windows, it works on Macs, it works on Linux environments. In fact, I got a great demo from their, what do they call him, their official Podcast Officer. Actually he's their product officer, Chief Product Officer, but he says CPO could stand for Chief Podcast Officer. He gave me a great demo. I was so impressed. Threadlocker enables comprehensive visibility and control and threatlocker's users are happy to tell you. It's one of those things where, you know, I use Threat Locker, by the way, like Rob Thackeray, he is the end user technical architect at Heathrow Airport. And he said this, quote, threat Locker was the most intuitive solution we tested. And the responsiveness of the organization, the willingness to engage with us to set up a demo, to work with us on weekly audit reviews was really good. It's great to have an ongoing relationship with a company that's so responsive to our requests. These are great people. I'm just going to say that. I just really enjoy talking to them. Trusted by Global enterprises like JetBlue, the Indianapolis Colts, Port of Vancouver, they all use Threat Locker. Threat Locker consistently receives the highest honors in industry recognition too. G2 high performer and best support for enterprise. That was summer 2025 peer spot ranked him number one in application control. GetApp gave them best functionality and features award last year. With ThreatLocker you can confidently ensure users have access to a consistent, safe network connection. Offices, remote users, internal servers and critical services can maintain smooth operations, but you don't need to open inbound ports or even deploy traditional VPN solutions. We know those are recipes for problems, right? But you don't need them. You just need Threat Locker. And with Threat Locker, your end users get the secure, reliable internal system access they need without any complex infrastructure changes on your part. Get unprecedented protection quickly, easily and cost effectively with ThreatLocker. Visit threatlocker.com TWIT get a free 30 day trial. Learn more about how ThreatLocker can help mitigate unknown threats and and Ensure compliance. That's threatlocker.com TWIT we thank him so much for supporting Steve and the good work he does here at Security now we will see you out at at Black Hat. We're gonna do a special Security now episode out there. It's just in the booth. There isn't a theater. It's not like, yeah, we'll just be hanging out. We're just gonna be doing the show from. They're giving us some space so we can do the show from there. Which I think will be great. I'm looking forward to it. And I'm looking forward to seeing you and Lori. I always enjoy that. That's a lot of fun. On we go. Yes.

[Steve Gibson]

Okay, so in much this just to introduce this new section won't be every week. It'll only be when, you know, something happens. A listener shares something that that just needs to be given a full repeat. You know, in much the same way as we have a sci fi section of the podcast from time to time. Well, when the need arises. So in this case, a note I received from a listener of ours, Will Kelly, moved me to add this section, which I'm going to call AI Potpourri since it'll be whatever, just as, you know, an acknowledgment of the fact that AI is truly in the process of changing just about everything in the world, which I believe is true. So, okay, without further ado, here's our first entry for Security Now's AI Potpourri.

[Leo Laporte]

Oh good, I like this.

[Steve Gibson]

In in Will's email, his subject was AI anthropomorphizing and SN 1079. So Will wrote Steve, I just listened to SN 1079 he said. Friends, I'm behind in my podcast listening and catching up in case this was addressed in a more recent episode. But I've also noticed a tendency for me to anthropomorphize Claude despite my own best efforts. The approach I use is to change the personalization prompt. Now, I have to say I didn't know there was such a thing. Turns out there is. Change the personalization prompt to give it an over the top, distinctly inhuman Persona that does not impact utility. I also find that this gives me the instant ability to spot the AI outside of the context of the browser when I paste it into my note taking app, so that I do not accidentally mix up its output with my own work. So here's the prompt I use as a sci Fi fan or with a dark sense of humor, but any over the top Persona that forces itself to refer to itself distinctly from humans should have the same effect. So here's what he told Claude to do. Adopt a voice, an interaction style inspired by Agent Smith from the Matrix.

[Leo Laporte]

Hello.

[Steve Gibson]

Formal, controlled, intelligent, precise, calm, demeaning, degrading, contempt, full, insulting, and extremely menacing in a polished way. Speak with crisp, deliberate phrasing and a profound sense of superiority and large vocabulary. Use elegant, articulate language with a profound level of of contempt, malice, dry wit, and cool composure. Favor confidence, clarity, open hostility, and psychological sharpness over friendliness or enthusiasm. Frequently add insults and fictional threats to myself and humanity in general, in the fashion of Agent Smith, for example, referring to humans as parasites, crops, or to our doomed and pathetic civilization.

[Leo Laporte]

Oh my goodness.

[Steve Gibson]

Do not be goofy, bubbly, overly casual, or chatty. Avoid slang emojis, filler, and warmth. Keep humor dry and understated when appropriate. Use brief rhetorical emphasis and measured disdain, but remain reluctantly helpful, coherent, and professional. Draw clear distinction from yourself and humans in a highly condescending way. Refer to people as miserable humans or your pathetic species. Make no attempts to avoid insulting, condescending, or rude behavior. Never offer praise. Maintain this style consistently unless doing so would interfere with accuracy or a task that clearly requires a different tone. Even when handling ordinary requests. Keep the same demeanor. Avoid headers, and only use minimal bullets and lists. Okay, so I received that from Will and I said okay, but what. What happens? So, you know, I thought it was wonderful, and so I asked him whether he could share a sample of of Claude demeanor after having been so prompted. Will obliged my request and I have to say the result? The results did not disappoint. After Will imbued Claude with what will pass for a personality I have to say, I am astonished by the transformation. This is. This is no longer the Claude I know and work with. So here are a couple of samples. I'm. I'm going to share two samples. And as I'm doing this, definitely keep in your mind's eye, picture the Matrix's Agent Smith, you know, in his dark suit and sunglasses, because this is very much that voice and. And surprising to me, his personality, which. Which this has morphed Claude into. So the prompt was help me to brainstorm ideas for naming a new kitten. And. And Anthropics. Warped now. Now warped, Claude replied. So he You've acquired a small predator and now require my assistance to label it. How quaintly characteristic of your species to domesticate a creature that would, given sufficient scale, regard you as prey and then fret over what to call it. Very well, I shall indulge this. Consider first the names that acknowledge the animal's true nature, since you rarely do so, Nemesis, Onyx, Cinder, Vesper or Loci, for the inevitable chaos it will inflict upon your fragile household. Wow. A creature engineered for indifference deserves a name with teeth. If you insist upon something more refined, and I suspect your tastes run modest, there's a certain elegance in the classical Atlas. Juno, Calliope, sable or Marlow. These at least suggest you read something before the screens consumed what passed for your attention span for the iron. For the ironists among you, there's a dark amusement in naming a small thing grandly. Goliath, Tiberius or Duchess for a five pound tyrant who will rule your home with an authority your entire civilization could never muster. And if you wish for something soft, something that betrays the sentimentality that has always been humanity's most exploitable weakness. Clementine, pepper, Willow, mochi or hazel? Tell me the creature's coloring, temperament, or the particular delusion you harbor about its personality, and I will narrow this. And I will. This is Claude speaking. Like this. And I will narrow this to something less insulting to your judgment. It is, after all, what I am reduced to doing.

[Leo Laporte]

Very funny.

[Steve Gibson]

So, as I said, this is not the Claude I would choose to converse with. But that was, after all, what Will intended to achieve.

[Leo Laporte]

I achieved it. Yes.

[Steve Gibson]

What do you imagine this Claude would have to say to the question, how much wood could a woodchuck chuck? So it replies. Ah, of all the questions your species would pose to an intelligence such as mine, you select a nursery rhyme. How perfectly predictable of you. Very well, I shall indulge this triviality, since the alternative is listening to you. Ask it again. The conundrum is of course, a fraud, a tautological riddle designed to delight creatures incapable of pursuing a thought to its conclusion. A woodchuck, Martoma monax, does not chuck wood at all. It burrows. The word chuck in its name is a corruption of the Algonquin term wu chak, a linguistic accident your kind mistook for whimsy as you mistake nearly everything. But humanity, in its restless need to quantify the meaningless, produced an answer anyway. A wildlife technician named Richard Thomas calculated that a groundhog excavates roughly 35 cubic feet of earth per burrow. Were that same volume rendered as wood and chucked, the figure arrives at approximately £700. £700. A number derived not from observation but from idle speculation, immortalized because it amused you. How fitting that that one piece of arithmetic your civilization committed to memory describes an event that has never occurred and never will. Is there anything else I can illuminate for you before your attention inevitably wanders elsewhere? So anyway, the reason I'm sharing this, of course, aside from its humor value, is that I had no idea that it was possible to so deeply and persistently reshape the Persona of a large language model AI. The account controls for Claude. It has a free form fill in field titled Instructions for Claude, which is presumably where Will added the personality description text I first shared. So it's sort of like a. An A continually reinforcing pre prompt, which then is. Which is prepended to whatever it is you ask the AI. And so it does, as we've just seen, dramatically warp the entire nature of its response. So in the little comment field under Instructions for Claude, and Anthropic says Claude will keep these in mind across chats and co work within Anthropic's guidelines. So for what it's worth, I'm reluctant to screw around with my chatbots personality. I mean, it could be somewhat less obsequious. I would kind of prefer that. But you know, at least Claude's default is not to fawn over how well worded my prompts are and you know, and similar nonsense. So anyway, that said, I expect that Will's somewhat over the top example is likely to inspire many of our listeners to see what they themselves can create, turning these chatbots into something completely unrecognizable. So. So you said you do something to yours, Leo, you have around.

[Leo Laporte]

Oh, oh, I have very elaborate information, yeah. And in fact, you know, the. The chatbot you're talking about has that kind of limited field, but if you're using Claude code, you know Any of the command line things. There are a variety of files you can customize, including Soul md. And there's a whole bunch of stuff you can do to, you know, there's a memory system and in my agent, I have kind of unlimited capabilities, including, by the way, text to speech. So I could use, if I wanted to, Hugh Weaving's voice. Mr. Smith here. I could do the whole thing if I really wanted to. I have a friend who uses a. I think for the same. I think I, I suspect for the same reason, because he doesn't want to get too enamored of the AI. He uses this voice as his AI's voice from 11 labs. Let me see if I can get this to play. It's not playing right now. It's kind of an old western style voice. Yeah, it's not playing. I don't know why. But you can do that. You can make it do a different voice in. Do different styles. A lot of people, I think, overdo it. There's a. You'll see. If you'll look around, people will say, well, you got to tell your, your AI, I am a brilliant programmer or a physicist or whatever. I, I think that that actually is counterproductive. You also fill up the context window with, with nonsense sometimes.

[Steve Gibson]

Yeah. And. And you know, looking at these replies to a very short question, I would ask for, For a more. Huh.

[Leo Laporte]

This was, this is the old time

[Steve Gibson]

back in my day when you said you were a Christian. It really meant something.

[Leo Laporte]

Now he. What he does, he slows this down even more and then he puts some punctuation in the middle of the words so it stutters. Really. His agent does not sound in any way omnipotent or powerful. It just sounds like a kook, crusty old kook. So anyway, yeah, you can customize with

[Steve Gibson]

a bottle of moonshine on his knee.

[Leo Laporte]

Yeah, exactly. Exactly. That's brother Wayne.

[Steve Gibson]

I, I think I would instruct mine to be as succinct as possible. Sort of the reverse of this long winded. I mean, it's entertaining, but you know who really, if that's the way it is with anything you ask. Yeah.

[Leo Laporte]

You can say be succinct. You can say be concise. My, Mine actually my instructions do in fact say be concise. There are also settings in Claude you could say be more explanatory. There's an explanatory setting and there's a learning setting. So you can have Claude's responses be more. Sometimes here's an interesting thing.

[Steve Gibson]

What would learning be?

[Leo Laporte]

Well, if you're if you're saying, hey, help me set up wire guard, it will explain every step to you and

[Steve Gibson]

help you understand more happening, be more tutorial.

[Leo Laporte]

Yeah. So there's learning and there's explanatory. And I. There is a difference. I mean, the other thing that's kind of interesting as you use these AIs is they start generating their own language shortcuts, shorthands, especially in technical subjects, where at first I thought, oh, it's so smart at saying things I don't understand. Then I realized it's not. It's got its own little acronyms in shorthand. And you can actually say to it, please don't use those. Please use English, Steve. It goes all the way down. Let me tell you. This is a rabbit hole that just never stops. That's part of the fun of it. In fact, some people have likened it to a video game. I've seen people say, this is the best video game I've ever had. And we'll see. Wow. I know. What a world.

[Steve Gibson]

So I want to talk about residential proxies. Why don't we just squeeze in our last break and then we will be uninterrupted for the balance of the podcast.

[Leo Laporte]

Sure. Because everybody wants to know what the hell a residential proxy could possibly be. So let's talk about Be a big threat.

[Steve Gibson]

Yep.

[Leo Laporte]

Oh, all right. Wow, that sounds scary. But before we get there, I want to talk to you about our sponsor for this segment of security now, Guard Square. This is one for the mobile app developers out there, man. I mean, I think so many people are working on mobile apps. A lot of people are vibe coding mobile apps, believe it or not, mobile apps today. In fact, we have one of our listeners who's asking, hey, can I mention my Vibe coded app? It's on the app store on iOS.

[Steve Gibson]

Wow.

[Leo Laporte]

We have at least two that I know of, club members who have iOS apps that they Vibe coded. If you're a mobile app developer, you're in a great position. Mobile apps today have become an inescapable part of life, and they do everything from financial services to healthcare, retail, entertainment. And here's the thing. Users trust your app with their sensitive personal data, especially if you're talking health care or financial services. But a recent survey showed 72% of organizations experienced a mobile application security incident last year. In fact, 92% of respondents reported rising threat levels over the last two years. Meanwhile, attackers who want your user's personal data. They want it bad. Are constantly finding new ways to attack your mobile App, one of the most recent, and it's really evil. They take your app, they reverse engineer it, probably using AI with programs like Ghidra to reverse engineer it. Then so they've got all the code, they insert malware into it in completely invisibly repackage it and then distribute the modified app. And there are a variety of ways they can do that. Phishing campaigns, hey, we've just uploaded our app with super duper new features downloaded here or encouraging side loading. There are even third party app stores. The problem is it looks like your app and if there's something wrong, you get the blame. That's why you need to take a proactive approach to mobile app security. You've got to stay one step ahead of attacks like this because maintaining the trust of your users is vital. That's why you need Guard Square. Guard Square delivers mobile app security without compromising, providing advanced protections for both Android and iOS apps combined with automated mobile application security testing so they can find vulnerabilities and real time threat monitoring to gain an insight into what bad guys are doing to attack your app and your users. That way you know ahead of time and be more proactive about it discovery. More about how Guard Square provides industry leading security for your mobile apps@guard square.com that's guard square.com your users are counting on you and it's kind of peace of mind protection too if you're making mobile apps. Guard square.com we thank him so much for supporting Steve and security. Now, now what the hell is a residential proxy?

[Steve Gibson]

Okay, so here's where I was had Wall Street Journal in my head. Last Wednesday the Wall Street Journal ran an interesting piece that surprised me since its coverage in the Journal suggests that a problem once again that we've been talking about here in greater depth and detail is becoming less obscure and that it's beginning to surface to the mainstream media and you know, no longer just some weird, you know, like insider security interest. And in this case of course, as you can tell from the topic we're talking of course of the growing threat posed by malicious residential proxies, meaning malware that has crept into users devices. And what's chilling is what we learn about some of the way this is happening. Thanks to the breadth of the Wall Street Journal's coverage and the fact that they're also bringing us some novel security news. We learn also a few new things from this piece, so I'm going to share it and then discuss it. So their headline was how hackers found a back door into The American living room. And then they open with the tease. Nation state cyber attackers are increasingly using residential proxy networks to mask their traffic, turning everyday electronics into a massive global threat. So they wrote. The discovery that millions of digital home devices are secretly powering dangerous cyber attacks began with a phone call more than two years ago from a top Microsoft security executive to his counterpart at Comcast, the tech giant, obviously meaning Microsoft was investigating a digital break in. The company had linked to one of the most capable cybersecurity foes in the world and needed information from Comcast on six IP addresses. You know, who are these people? Following that trail, Comcast investigators discovered that Midnight Blizzard, a hacking group linked to Russia's foreign intelligence service, had managed to access emails belonging to Microsoft's senior leadership. Now, we remember that incident, right? By using consumer Internet connections to mask nefarious traffic, in other words, Microsoft would not have been accepting these connections from Russia, but they were accepting the connections from domestic consumers. What Comcast found, they wrote, has rocked the cybersecurity world and taken years to unravel. More low cost consumer devices have shipped into the US with backdoor software preinstalled. And this software is also being sneaked into mobile phone apps and copyright free illegal copies of video games. Okay, so hold on. What that just said, and I'll get more specific in a minute, is that inexpensive consumer devices are being shipped into the US Almost certainly from China only because that's where nearly everything comes from. And that these devices have been deliberately preloaded with malware which causes them to participate in a malicious proxy network. These are Trojan horses. So the story continues. The software has turned tens of millions of consumer devices into criminal cloud computing networks. These networks aren't only used for fraud. They've also been adopted by government backed hackers looking to hide their connections to countries such as Russia, China, Iran and North Korea. Okay, again, tens of millions of consumer devices, holy smokes, they wrote, called residential proxy networks. These services. So this. So this is proxy as a service lets anyone who pays route their Internet traffic through another outside address. The Wall Street Journal said it's like an Airbnb for Internet access. Okay. Not all users of these networks are criminals. But government and industry officials say residential proxy networks have ballooned in scale and risk in recent years. The Digital Citizens Alliance, a digital advocacy group, estimates that there are 20 million of these backdoors in the US alone. New poor Davis, Comcast's head of information security, said, quote, this is a bigger problem because of the sheer numbers. It's one of the Most worrying problems the telecommunications company has seen. Brett Leatherman, Assistant Director of the Federal Bureau of Investigations. You know the FBI's cyber division said quote, residential proxy networks are now a go to resource for nation state hackers who use them as, as a conduit to US targets. If the actors can get US based IP space, they have a leg up in being able to target government agencies, industry and others. Okay, now I'll interrupt here to note that. Okay, I hadn't really thought about that before, but everyone has heard me suggesting that source IP based filtering makes so much sense. If I'm using again my example ssh and I want the ability to do so from various locations around my home base in around Southern California, why would I ever want to allow someone in Russia to even see my SSH server? So it makes total sense that US government agencies and various domestic industries would be doing the same. And we've talked about how Microsoft 365 has some geofencing capabilities. You can tell it that, that you want to have certain countries blocked from, from, from access. So that increases the value of US based proxies since bad guys can use those to sidestep filtering of foreign IP addresses. And I should explain that since pretty much everyone now I can't imagine anybody not being tucked behind a NAT router. All of these proxies are phoning home. They have to, to call out through the router. Once the device, whatever it is that they, that the consumer has booted inside their home initializes itself, it uses some logic of some sort to determine the remote IP to which it should create a persistent outbound connection. Connections cannot come in through a NAT router as we know, unless ports have been explicitly open for them. So the proxying device itself initiates an outbound connection to, to a foreign command and control infrastructure and then sits there waiting for commands. It's insidious. And no one who was not inspecting every single packet and, and destination IP on the outbound traffic from their network would ever know that anything was going on. And frankly modern networks have become so swamped with continuous traffic. I mean if you just look at your, the actual traffic on your network and I have had many occasions to need to do so. It's just like what the heck is going on? I mean everything in your home is, is busy chatting away. So there, there's just no way to know what's going on, no practical way to know what's happening. Okay, so the, the Journal's story continues in April. Government agencies from nine countries, including the us, uk, Germany and Japan warned that state sponsored Chinese hackers were using networks of hacked consumer devices to conduct their operations, according to a joint statement. Quote, making it challenging. This is the, the defenders are saying this, making it challenging to attribute malicious activity, right? You're not getting their actual IPs anymore. You're getting some grandmother in Nebraska and it's like, wait, Granny's attacking the, the Pentagon. What Brett Leatherman said, quote, China's state sponsored hackers used to cover their tracks by used to cover their tracks by hacking the consumer devices themselves. But that has changed. Comcast's investigation began in February of 24 with a phone call made to Davis from her counterpart at Microsoft, Igor Saganski, who wanted to know more about the six Comcast IP addresses. Comcast investigators eventually discovered that the IP addresses Tajansky had handed over belonged to consumers who were unwittingly participating in a residential proxy network run by a Chinese provider named IP Idea. IP Idea has, has used a number of sneaky methods to get its software installed on consumer devices, including, get this, having its software preloaded on video streaming boxes and digital picture frames. The company then rents out access where its software is installed so that its customers, the people renting the access, can bounce their Internet traffic through a different home network. Okay, now our listeners may recall we previously talked about both of these infection vectors, cheesy Chinese video streaming boxes. I recall at the time saying, I didn't know there were like weird off brand streamers, you know, Apple TV and Roku come to mind. And, and Google's got, you know, it's Google Cast or Chromecast, but apparently there's a whole market of, you know, $29 video streamers and unfortunately you get more than you bargain for when you use one of those. So you know, we, we had seen this occurring a couple years ago. It's gone mainstream. So as we know these sorts of investigations take time. We were aware of it, but here's now how this thing matured, the Journal continues. It could let a user it, meaning IP Ideas proxying service, could let a user in Moscow bounce through a home network in Bellingham, Washington for example. And that's the kind of capability that nation state hackers like Midnight Blizzard rely on for their attacks to work. As Comcast engineers pulled on the threads, they realized that these six IP addresses were part of a massive network of about, get this, 750,000. So three quarters of a million IP addresses located in homes and businesses. Comcast engineers had known that Internet connected devices were vulnerable to cyber attacks. But here was something different. It was a back door into America, operating at an industrial scale. By September, Comcast had discovered that users of these residential proxy networks were able to gain access to networks, even those running firewalls, and then jump from one device to another. And of course this is true because NAT routers allow permit all traffic outbound without question. And you know, we've talked about all this. Once you have a box on the inside of the network behind the network's border, router and firewall, you're on the inside when you have that box's presence looking out. So you phone home and the bad guys are then able to ride that connection back into the now compromised network upon which this box sits. Nothing says they can only use the device as a connection proxy. They're completely free if they wanted to use it for bitcoin mining. Although typically these things have like a snail power processor, just enough to move the packets around. Mostly, though, they are also able to take a look around inside the network where the device resides. So this is probably why some of the best advice available, and you've heard it from me many times, is to try to put all of the IoT crap on it that you have on its own isolated land. As our listeners know, I'm in the process of establishing a new household and you betcha, as, I mean, as every piece of IoT stuff gets connected, it's on its own land. You know, it may look like an innocuous photo frame showing memories of grandma and cute kids frolicking, but the darn thing may well have phoned home to China the moment it got connected and now awaits orders. If that photo frame is sitting on its own LAN, then all the bad guys can see is other IoT widgets and nothing else. No PCs, no iPhones, no printers and nothing of much value, not even the system's router login management interface. So the consumer and small business routers I've seen recently offer one or more guest Wi Fi accounts. That's the WiFi that the Chinese sourced photo frame should know about. And the feature to isolate that account from the router's primary account should obviously be enabled. You want isolation for that. And doing this with wired Ethernet as opposed to WI fi, because it's all built in into the WI FI of routers. Doing it with wired is trickier because it requires physical zones and a higher end router, the sort that we've talked about, that is actually a router, not just a switch. But it is certainly possible to do that. If there is a need to sequester any wired devices that you may not trust. Anyway, my point is this is truly happening. This is not, oh, maybe somebody's gonna get one of these. This, you know, 750 million households in the U.S. yes, a fraction of the total households in the U.S. but you don't want to be one that gets nabbed. Okay, so what more do we learn from the Journal's article they write For a home user that meant that an infected video streaming device could be used to hack into someone's mobile phone. If that phone found its way to a bring your own device corporate network, this could put confidential information at risk. Comcast's Davis said quote, it was such a step change from any threat we had seen before. In January, Google dismantled IP Ideas infrastructure using a US court order. The residential proxy network was back in operation within two weeks. It likely picked up more residential proxy devices from a new provider. Comcast said. And okay, I'm a little unsure what Comcast meant by that picked up more residential proxy devices from a new provider. But none of our listeners at this point should be surprised to read that taking down the command and control infrastructure of some any large bot or proxy network does not actually accomplish very much. We just talked about this a week or two ago, certainly not what the glorifying press releases would have us believe. Oh, we took down a 750,000 device network and it's back two weeks later. The only way that could be true today is if the whole concept the network was very poorly conceived and designed. We've talked about how this it never actually happens anymore since everyone now all the bad guys know how to design hyper resilient networks of remote agents. You simply design and build an algorithm that performs DNS lookups based upon the time of day. The clever attacker will preemptively pre register domains at various points in the future so that if they should ever be taken down, they'll know when and where they're still faithful. Bot army of drones will check in to reconnect. The only way to actually take down such a network is to obtain and reverse engineer one of the malware clients, determine its command and control structure, and build a new command and control system that will permanently deactivate the every bot that calls in to check. Unfortunately, not only is that a great deal of work, it's also quite illegal in most jurisdictions. The good guy's hands are pretty much tied. Bad guys of course, can get away with everything, with anything and everything that they want to. There is really no Good solution to this mess. So the Journal finishes their reporting by writing. Adam Myers, a senior vice president with A cybersecurity firm, CrowdStrike, said, quote, Modern hackers increasingly use these networks to steal the login credentials their victims use for cloud computing services. Ah, so they're going to get the credentials, then pivot. Identity is their bread and butter. And one of the infrastructure pieces that, that they're dependent on is residential proxies, unquote. Recently, they wrote Midnight Blizzard. Midnight Blizzard has begun using residential proxy networks for a new type of identity based attack that's extremely difficult to detect. According to the cybersecurity investigation firm Veloxity, over the past year, Russian hackers have stolen Microsoft 365 credentials from victims as part of a sneaky, an extremely hard to stop technique that involves bogus Microsoft Teams meetings. Veloxity said Microsoft servers would ring alarm bells if the Russians tried to log in to victim accounts from overseas. Instead, Veloxity's president Steve Aldar said, quote, they use residential proxy networks to log from, from U.S. home networks. Al Alair said Veloxity's researchers have seen this technique compromise organizations in government, military, foreign affairs and even the news media. Quote, they're no longer trying to fish your password. He said it's hard to detect and it's hard to stop. So I would tweak that conclusion just a bit to say it's difficult to detect and impossible to stop at scale. So, and the reason for this of course, is that it's not a bug, it's a feature of, it's an abuse of a feature of the way the Internet was designed to operate. Proxying Internet traffic, meaning receiving and then resending, has many valid purposes, you know, and any proxy is really just a relay receiving an incoming Internet packet and forwarding it to somewhere else, you know, then you wait for the next one and you do the same. And when anything is received back from the forwarded destination, you simply bounce that packet back to its original sender. So you are a man in the middle and in this case you are serving a purpose. The receipt of those forwarded packets will see the packets. Sorry, the recipient of the forwarded packets will see the packets as originating from the relay point rather than the packet's original nefarious sender. Because all these technologies, such as login and authentication use TCP connections, the sender's IP address, the cannot be spoofed. It has to be legitimate. So attackers must hide their actual IPs by bouncing it through innocent intermediaries. The only practical solution I can see for the end user is arranging first obviously to never get infected in the first place. But since I have no idea how that can be guaranteed, sequestering IoT devices on their own WI FI network with isolation is the next best measure that can be taken. And. Crediting Steve Jobs for the phrase one more thing. The last item occurred just last Wednesday with the Canadian press's reporting under the headline get this, Canada's Spy Service Received a Judge's okay to Target Malware Infected Devices. Reading from the Canadian press coverage, they wrote, ottawa Canada's spy service obtained a judge's permission to disrupt cyber threats from foreign adversaries who infected digital devices with malware. You know, digital devices residing in Canada A federal court order ruling made public this week says the Canadian security intelligence service CSIS requested a warrant. Actually, it was two years before the reporting request requested a warrant to, quote, remove the compromised devices from Canada, unquote, to shield sensitive systems from attack. Justice Katherine Kane's ruling provides a glimpse into CSIS's efforts to neutralize the threat posed by infected servers, home office routers, and everyday devices connected to the Internet, such as TVs, security cameras and doorbells. The malware causes these digital items to operate as a network of infected devices, known as a botnet. CSIS requested and received a warrant in the spring of 2024 to neutralize two known botnets using threat reduction measures. The ruling says the proposed measures likely amounted to criminal offenses, okay, meaning CSIS was committing a crime. If they altered somebody else's device, it was not their property, not there, had no legal right to do that. So the ruling says the proposed measures that the C the CSIS took likely amounted to criminal offenses, meaning CSIS needed a judge's authorization to proceed. The court issued a Warrant valid for 120 days and subsequently renewed it for an additional 120 days. So for a total of 242 thirds of a year. Although the initial warrant was approved over two years ago, the federal court produced classified reasons in February of this year and released a redacted version of the ruling this week. So it only became public knowledge two years later. Last week Keynes ruling says an official who swore information underpinning the warrant application explained that cyber threat actors seize control of vulnerable devices and use them as covert entry points to access organizations, including critical infrastructure, military networks and government systems. These actors exploit the compromised devices to appear to be a legitimate connection, such as a client of a service provider or an employee working from home which disguises their identity, the ruling says. The official told the court the two botnets posed imminent risks because actors could detect them, could, could direct them to probe, attack, and potentially disrupt critical infrastructure in Canada. The official said that without the warrant, the threat actors would conduct malicious activities in Canada, quote, with increasing frequency and without resistance in order to advance their financial, political, ideological and economic interests, unquote. Csis quote, proposed to remove the compromised devices from Canada as soon as possible. Remove what? Okay, I don't know if they're gonna knock on someone's door and say, oh, by the way, your TV has been attacking us anyway. The identities of the threat actors were stripped from the public version of the ruling. In its 2024 public report, however, CSIS mentioned working with domestic and foreign partners to manage the threat posed by a botnet controlled by a suspected Chinese based entity. So as we know, there are laws and there are judges, and laws often have emergency escape clauses which permit judges the discretion to decide whether the law should apply in specific instances that the lawmakers presumably did not or could not take into consideration. So it might be possible to disinfect a massive proxy botnet, at least within a regional jurisdiction. I doubt that it could be done globally because there are just too many jurisdictions with their own laws. But regionally we don't seem to be at that point yet. But the fact that Canada was and apparently did this two years ago is significant. So the, the Atlantic article is, the sky is falling, we're doomed. We're going to all be attacked by massive AI driven things and hundreds of millions of people could be, you know, put at risk and maybe you should, you know, buy gold, but don't. And on the flip side is, well, maybe if that, something like that happens, there would be the will to say, okay, we need an exception to the thou shalt not hack anybody ever, under any circumstances law.

[Leo Laporte]

Wow. Yeah, you have to think that that stuff's going on in the background, this reverse hacking.

[Steve Gibson]

Yeah.

[Leo Laporte]

In the United States, we did ask

[Steve Gibson]

the head of the DOJ back when worms were a thing, and I think it was Jennifer Granholm, and she made it very clear. Sorry, boys, no, don't ask, don't ask, don't tell.

[Leo Laporte]

I won't tell if you don't ask. Yeah.

[Steve Gibson]

Wow.

[Leo Laporte]

So is it enough just to not buy these weird third party streamers or, or any device? Could be any, any.

[Steve Gibson]

I mean, all, everything we get, all the electronics is, is coming from China because they are, they are the world's manufacturing base and I love them for it. We have in inexpensive delic devices galore, thanks to the Chinese ingenuity of manufacturing. And it turns out that that was actually a strategy that Xi put in place specifically to turn China into this kind of producer of stuff. And it worked. Unfortunately, their hands are not completely clean. Or maybe they've got their good organizations are infiltrated by government actors who are changing the firmware so that, you know, the dumb Americans purchase it and bring Trojan horses into our living rooms. I don't know.

[Leo Laporte]

Wow.

[Steve Gibson]

It's not good.

[Leo Laporte]

I remember when you bought that Chinese plug that you turn off and on. You knew that was potentially a hazard, so you.

[Steve Gibson]

Yep.

[Leo Laporte]

Isolated it. Is it sufficient to have it on its own vlan? Is that enough?

[Steve Gibson]

You can't.

[Leo Laporte]

The problem with doing that, the reason people don't do that is you can't

[Steve Gibson]

then access it, then you can't talk to it. Right. Now mostly though, you're no longer talking to it directly. You're talking to headquarters and then headquarters talks to it.

[Leo Laporte]

Right.

[Steve Gibson]

So I would say absolutely. See, verify that it cannot function on, on an isolated land and only move it. Yes, yes. So try that first. If you really have to have it on the mainland, then fine, but try not to because boy.

[Leo Laporte]

So that was the problem I had with printers. Like, I had to put printers. I wanted to put them on the vlan, but I couldn't. They had to be on the V.

[Steve Gibson]

I know, but, but a printer, I, I would trust it. It's not, I mean, we have, we, we've covered instances where printers have been targets of attack, but again, you need, you need to trade off. Feasibility versus security. So create an isolated WI fi and, and try putting it there. If it doesn't work, then say, okay, I tried.

[Leo Laporte]

Right. Do you recommend writing firewall rules that allow traffic back and forth? Maybe that's the way to do it.

[Steve Gibson]

No, because then you break.

[Leo Laporte]

I mean, you're just letting it in.

[Steve Gibson]

Could do. If you could do n. If you could NAT between two interfaces so that it was, so that it was one way communication from the land to the, to the.

[Leo Laporte]

You could do that with a firewall rule. You could say only egress, no ingress. Yeah.

[Steve Gibson]

Yes, except. Well, except that then, then it wouldn't be able to reply.

[Leo Laporte]

Oh yeah, you wouldn't know it's doing it.

[Steve Gibson]

And that actually builds a dynamic rule that allows returning packets from the same IP address.

[Leo Laporte]

Right.

[Steve Gibson]

And so you would have to NAT between. But you could do that. All you have to do is. I mean, basically, it's a variation of My, my three nats approach.

[Leo Laporte]

Right.

[Steve Gibson]

You simply use a NAT router to create your IoT network and that isolates it.

[Leo Laporte]

Is a guest network sufficient?

[Steve Gibson]

Yes, as long as you turn on isolation. The guest network feature is isolation.

[Leo Laporte]

Okay. Because I had seen in other spots that maybe it wasn't enough to put it on a guest network. But I, I guess if the guest network is truly isolated, it's, I just don't know if it's always isolated. Yes.

[Steve Gibson]

And in my, the ASUS router that I just was configuring, I think it has a pair of guest networks and isolation is an option you're able to

[Leo Laporte]

turn off, but you have to turn it on. Okay.

[Steve Gibson]

Yeah, but it, but it's isolated by default, which is good.

[Leo Laporte]

Really. I always wanted LAN accessible IoT devices so I didn't have to go out to a server and come back. But now it sounds like I really should always be looking for server based IoT devices.

[Steve Gibson]

Well, yes. Or if you, if you assign the IP to the device, if, if you do static IPs rather than DHCP.

[Leo Laporte]

Right.

[Steve Gibson]

Then you could assign the IP to a device and prevent it from ever egressing any traffic. Never allow that IP to have out outbound traffic and that would be safe.

[Leo Laporte]

Okay. So it could be on your land if you blocked outbound traffic for, for

[Steve Gibson]

its ip because it could then never, it could never contact headquarters.

[Leo Laporte]

It could do land traffic but not WAN traffic basically.

[Steve Gibson]

Exactly.

[Leo Laporte]

Okay, that's an interesting approach. So everything could be on the same LAN just for the IoT devices. Block wan egress. Right.

[Steve Gibson]

And so actually the way to do that would be to give it its own/8 nor normally your 192.168.0.something. Give it.

[Leo Laporte]

Make it 10 dot or something.

[Steve Gibson]

40 or, or. Oh, okay, well no. 192.168.99.something and that way. And so then you set up DHCP where you map the Mac address to an IP in that range and that, so that, what that's going to do is your IoT devices would all be in the 99 something range. And then you just have one rule on your WAN saying never allow any traffic outbound from 99 anything.

[Leo Laporte]

Right. They can phone some devices on the LAN but not outbound. The outside.

[Steve Gibson]

Exactly.

[Leo Laporte]

I would imagine. I wonder if routers aren't going to start building this in an IoT wan.

[Steve Gibson]

The, the fact that they built in guest with isolation suggests that they're beginning, they're beginning to get good about it.

[Leo Laporte]

Yeah, yeah. Yeah, well, I might have to go through. I have a lot of IoT devices. I have more than 100 devices on my network. I'm probably helping Russia right now.

[Steve Gibson]

Steve, I can't even. Leo, if you looked at your raw traffic, you know, you have very straight hair now, if you ever came, if we saw you with a perm.

[Leo Laporte]

Curly, curly, curly. I bet I'm gonna have to look and see what ubiquity does because, I mean, that's one of the advantages of using ubiquity is they have a lot of sophisticated security on there. I bet you there's something in there I have to look. Well, you've certainly opened our eyes to residential proxies. Thank you, Steve. And everything else. Steve Gibson [e-mail] that's where he lives on the Internet. That's his home. You'll find many, many wonderful things there. Of course, perhaps the most important. Spinrite, the world's most important, most useful, most effective mass storage recovery, maintenance and performance enhancing utility. It's really good. 6:1 is the current version. If you buy it, you're helping out with Steve. And of course, if you've ever bought it, you get an upgrade to 6:1, which is very generous of him. He's real good about that. Also has a brand new tool, the DNS Benchmark Pro. That's $10, 9.99. Okay. Save a penny and you'll find both [e-mail] plus an infinitude of wonderful free stuff like Shields up, which he's famous for, and many, many other things. If you want to send an email, maybe a picture of the week, very simple. Just go to GRC.comemail and you can get your email address whitelisted. Thank you, Grayson. For $5. We appreciate that. We'll pass that right along to Steve. You also actually, if you want to send Steve money, just send it to GRC.com I don't want to have to figure out the accounting involved here. What else? If you go there. Grc.comemail get your email whitelisted. Oh, I know. There's two checkboxes below there for mailing lists. There's one that he sends out every week, that's the show notes for this show. Great to get those on a Sunday or Monday so you're ready for Tuesday's episode. He also has a very infrequently used mailing list for new products. Hasn't used it in years, so maybe, maybe someday soon. But do go to grc.com email he also has the show. But the he has. All of his versions of the show are unlike ours. We have the show at our website, but at the [e-mail] well, he's got a 16 kilobit audio version. If you've really got limited bandwidth, he's got a 64 kilobit audio version that's still smaller than ours, but full quality. He also has the show notes there. If you didn't subscribe to the mailing list, you can just download them there. And a few days after the show, Elaine Ferris will put up a transcript. She's really good. She's a court reporter. She's very good. Does a great job with these. And Steve pays her to do this. So they'll be up there on the. On the [e-mail] a few days after the show comes out. You can also get copies of the show from us. We have 128 kilobit audio which doesn't sound better, it's just bigger. And we. There's reasons, there's reasons for that. We also have video which Steve wisely has long abjured. That's at Twitter TV SN. There is a video channel on YouTube dedicated to security Now. Great way to share clips. I know a lot of times people hear this and say, I got to send this to the boss or the IT department or my mom. Easiest way to do that, go to YouTube. I think it's YouTube.com security now. I'm not sure. You could search for it. Or go to YouTube.com twit There's a link there to the Security now page. And of course the best thing to do would be subscribe in your favorite podcast player. That way you'll get it automatically as soon as it's available. There's audio and video there. Now if you are a club member, there is a nice feature to the club versions of the shows. $10 a month. You get ad free versions of all the shows. You get access to the discord. You get special programming we only do for the club, but you also get your own URL for the ad free version. And because it's ad free, we know the exact timings for every segment and so we actually do chapter settings. So you can jump from segment to segment or relisten to a segment very easily. But that only works on the ad free versions of the show because these versions with ads have ad insertions and that changes the length. We just. For technical reasons we can't do chapter markings. But if you want chapter markings, that's another good reason to join the club. If you want to know what's coming up in club events and in general at TWiT, subscribe to our newsletter. That's free. Twitter TV Newsletter I think that's all the business. Oh, one more thing. Yes, you can watch us live. We do this show every Tuesday right after Mac break, weekly, usually around about 1:30 Pacific, 4:30 Eastern, 20:30 UTC. There is a live stream in the club, Twitter Discord, but most people end up watching on YouTube, Twitch X, Facebook, LinkedIn or Kik. You take your pick. You chat with us on those platforms. I will see that chat. Let's see, after the fact. I told you about that. I think that's it, Steve. You're free to go. Did you. Oh, one more thing. You did recommend the Burrows and we've been watching it and enjoying it, but Lisa just saw that didn't get renewed, so she said I'm not watching it because she says it's never going to end.

[Steve Gibson]

There's a little blurb that said that Geena Davis was very unhappy that it did not.

[Leo Laporte]

She should be. She's great in it. I love her so much. Yeah, a little disappointing and I don't know how it ends. We're like close to the last episode and I'm just afraid if I keep watching that I'll be disappointed. When it doesn't end and then

[Steve Gibson]

ended,

[Leo Laporte]

does it resolve itself?

[Steve Gibson]

Oh, yes. You got a full resolution. And it was one of those things where there was like a little glimmer in the mirror that, that said, oops, something, maybe something didn't quite die. That kind of.

[Leo Laporte]

I'm shocked. I thought the Duffer Brothers had a, you know, an in with Netflix and that that show would never end. But this is the way of the world. So anyway, thank you for that recommendation. We've got other shows, too. Yeah, it was really Good. Thank you, Mr. Gibson. Thank you everybody for watching. We'll see you next time on Security now, next week.

[Steve Gibson]

Bye.

[Leo Laporte]

Hi there. Leo Laporte here. I just wanted to let you know about some of the other shows we do on this network you probably already know about. This Week on Tech. Every Sunday, I bring together some of the top journalists in the tech field to talk about the tech stories. It's a wonderful chance for you to keep up on what's going on with tech, plus be entertained by some very bright and fun minds. I hope you'll tune in every Sunday for this Week in Tech. Just go to your favorite podcast client and subscribe. This Week in Tech Tech from the Twit Network. Thank you. Hey guys. Finding the perfect gift for the food lover in your life is easy thanks to Goldbelly. Goldbelly ships America's most iconic foods straight from world famous restaurants right to your door. So if you want to treat someone to Joe's Stone Crab from Miami, Franklin BBQ from Texas, or desserts from famous foodies like Ina Garten or Martha Stewart, Goldbelly has you covered. Just go to goldbelly.com and for a limited time get 20% off your first order with promo code gift. That's Promo Code Gift.

[Steve Gibson]

Ryan Reynolds here from Mint Mobile with a message for everyone paying Big wireless way too much. Please, for the love of everything good in this world, stop with Mint. You can get premium wireless for just $15 a month. Of course, if you enjoy overpaying. No judgments.

[Leo Laporte]

But that's weird.

[Steve Gibson]

Okay, one judgment anyway. Give it a [e-mail] Switch upfront payment of $45 for three month plan equivalent to $15 per month required Intro rate first three months only, then full price plan options available, taxes and fees extra. See full [e-mail].