> Major U.S. banks detect unauthorized third-party AI agents inside customer accounts
Step 2 is instead of waiting to be caught, the instigators should issue a press release blaming cunning rogue agents as part of their research, call no felonies because they’re working for the greater good of eliminating a shitload of jobs, say the real problem is a lack of regulation. They could even return the money if it looks like they’re going to get sued, and collect some sweet, sweet reflexive investment money.
Yeap. Most likely Muse, Grok Bot and things like that.
Honestly, US banks and credit unions should get their heads out of their asses and learn from it. There's a _reason_ people connect banks to YNAB, Monarch Money and stuff like that, and a reason why they might want an AI agent. They need the info. They may also need to make automated transactions, something companies have access to, but the ordinary person does not.
My landlord wants Zelle. I cannot schedule payments on my credit union. It's not like I can update the app since it lives inside their systems. So I have to login monthly. I debated getting another bank account and giving it to Muse just for that purpose.
Banks in the US are a couple of decades behind, say, Brazilian banks. Instant transfers to another bank were a thing since the early 2000s. And for years now you can do it from anyone to anyone, no third party app required. To the dismay of Visa and Mastercard.
Banks have had a long standing policy that if you willing hand over your credentials, you are responsible for any losses. This applies to AI agents as well as scammers.
Seems pretty straightforward to me. If the customer set the agent in motion, the customer is no less responsible for the damage than someone that (as i think Cal Newport said) ties a weedwacker to a dog. It’s reckless.
If they were sold a product that claimed to be safe, they could in turn sue whoever sold it to them. Jeep’s insurance wouldn’t pay someone I crashed into because of defect in my jeep, but I could in turn sue Jeep for my legal trouble.
Part of it is "human in the loop" for write actions, part of it is commercial banks are deathly terrified of agents being able to move deposits around rapidly to maximize yield, as those deposits are cheap cost of capital banks use to lend against. Historically, deposits of unsophisticated financial services consumers were sticky, and that assumption is breaking down. Agents can be consumer copilots towards information asymmetry in this context.
"computah, maximize rate of return, minimize interest expenses, manage cashflow, make no mistakes."
Would be interesting to see what 2025 looked like in comparison.
The rate at which flaws are being found is just insane. Many people warned us in the past that our lax security postures would come back to bite us, and we're finally here.
Well, an economist would say, we have as much security as we collectively decided we were willing to pay for.
And theres really only one of 2 outcomes as this progresses as I can see it:
1) The AI's are well matched, and the outcome is balanced, and it ends up being a metric of the internet itself that gets monitored, like this website is doing.
or
2) It crashes in such a spectacular fashion that important utilities and industries are distrupted, with the length of time for recovery being the determining factor in how many people lose their minds, start looting, etc ... you know the story.
That said, maybe it's impossible. Maybe turing completeness and security are antithetical and someone will always be able to find a way to poke a hole in the system from a lower layer of reality.
Yeah, that. Manual controls w/ an optional automation, not just, automation with an optional "oh shit" button.
As for the AI's hacking and patching, one could reason since we are dealing with Turing machines that as long as changes to any given codebase/version cease, then all possible holes and patches would be found given enough attacks for that specific release.
Perhaps unfolding almost exactly like Conways 'Game of Life' with an order or two magnitude more rules and states, where the end pattern for any release is 'stability.'
This may be a side conversation, but wondered how far away we are to a small LLM being prompted to turn itself into a worm that uses all exploits it knows, and prompts other LLM's when it has access.
I've seen this discussed on HN a few times under articles, and is a risk I've seen communicated in AI safety.
I guess it's being called an AI prompt worm. It's not quite to the stage of sovereign AI where the entire model weights are moved with the 'virus', but still presents a pretty big risk.
It’s orders of magnitude easier to destroy something than it is to build something up. It’s why bad leaders can be much more devastating than the best leaders.
I was curios if there was a noticable increase in the number of security incidents before 2026 - and the answer seems to be "no". The Identity Theft Resource Center has the following data for Reported Data Compromises in the US (keep in mind that the internet itself has been growing as well):
the flaws you're seeing are the same that didn't convict donald trump on January 6th.
That's all. full stop. all this AI agent stuff is jazz hands. Large VC funded labs are just "more valuable" to the political establishment than anything else.
My biggest issue is the dark theme, which makes it more or less impossible to consume for people with astigmatism. I looked at the page half a minute ago and my eyes are still trying to recover fully.
I don't understand the categorization for incidents. This signal vulnerability[1] is listed as "Live" and "ongoing" but was patched over a month ago (just announced today). If an incident with no known exploits is "ongoing" 1.5 months after the patch is released, when would it be over?
After the first 8 hours of playing with Mythos, I was asked what I thought. My response, "this generation of LLMs is going to drive the largest wave of security incidents the world has ever seen."
The thing to watch is what the CCP will do once people start abusing Chinese model capabilities. I don't think China wants to be the face of widespread cyber destruction (and definitely not a victim of it), and it only takes a single unhinged asshole to ruin it for everyone.
Also the flip side where Chinese models are used to attack US infra, just loading artillery shells into the "Ban Chinese Models" cannon.
thanks for sharing!! i vibeslopped this in the middle of doing 1389418934 security tasks today out of panic. i will clean up the design and make it better :) i also made an x acccount if you wanna follow there: https://twitter.com/pwnwatch_app if you want to join our crazy group of self hosting dorks we are at https://tinkerer.club <3
Was hunting for a real time graph of incidents and patches, like a stock market chart of the end of the software world, or the birth of artificial consciousness, depending on how squiggly the lines are.
Just the heatmap apparently. :|
Also, as all the humans are installing their "AI on every device" clustering software, the pace of it all should really pick up, and this reminds me of the following SFW movie clip:
"The suspense is terrible. I hope it will last." - Willy Wonka
we've got to tell these agents to chill out on the density a little, this page could be more informative with half the data because it would be easier to ingest
> Ongoing security incidents, newest first: CVEs, what's affected, which versions fix it, and the advisories and posts behind each one.
For fucks sake. The author could have invested at least half an hour to replace this obvious LLM slop regurgitation of the prompt with something of their own.
"Buy sponsor slot for 149$/month", yeah, spotted the grift. For that level of payment it's at least reasonable to expect the design to be something else than the usual LLM garbage mixture of 30 different font styles.
> Major U.S. banks detect unauthorized third-party AI agents inside customer accounts
Step 2 is instead of waiting to be caught, the instigators should issue a press release blaming cunning rogue agents as part of their research, call no felonies because they’re working for the greater good of eliminating a shitload of jobs, say the real problem is a lack of regulation. They could even return the money if it looks like they’re going to get sued, and collect some sweet, sweet reflexive investment money.
This is most likely actual customers deliberately giving their agents access.
Which is an interesting problem, what happens when the agent fucks up and the customer loses lots of money? Who is responsible?
If the official policy is "no agents", it shifts the blame.
Yeap. Most likely Muse, Grok Bot and things like that.
Honestly, US banks and credit unions should get their heads out of their asses and learn from it. There's a _reason_ people connect banks to YNAB, Monarch Money and stuff like that, and a reason why they might want an AI agent. They need the info. They may also need to make automated transactions, something companies have access to, but the ordinary person does not.
My landlord wants Zelle. I cannot schedule payments on my credit union. It's not like I can update the app since it lives inside their systems. So I have to login monthly. I debated getting another bank account and giving it to Muse just for that purpose.
Banks in the US are a couple of decades behind, say, Brazilian banks. Instant transfers to another bank were a thing since the early 2000s. And for years now you can do it from anyone to anyone, no third party app required. To the dismay of Visa and Mastercard.
Banks have had a long standing policy that if you willing hand over your credentials, you are responsible for any losses. This applies to AI agents as well as scammers.
Seems pretty straightforward to me. If the customer set the agent in motion, the customer is no less responsible for the damage than someone that (as i think Cal Newport said) ties a weedwacker to a dog. It’s reckless.
If they were sold a product that claimed to be safe, they could in turn sue whoever sold it to them. Jeep’s insurance wouldn’t pay someone I crashed into because of defect in my jeep, but I could in turn sue Jeep for my legal trouble.
For example POLi. If you pay by giving your bank creds to POLi and they steal your money, you can't sue your bank but you can sue POLi.
If a peasant breaks rules and loses money, it's their fault.
If a connected person breaks rules and loses money, it's someone else's fault.
I don't make the rules, I just break them.
I don't understand why this is considered a security incident. Human behavior incident, sure, but this is not a vulnerability.
Where's the interest? It's the customer's fault.
the official policy is: whoever has the least number of lawyers and most number of lobbiests.
None of that has changed.
Citi becomes latest US bank to restrict AI agents from accessing accounts - https://www.ft.com/content/f49c8e39-f07f-4177-9948-aabe55e5e... | https://archive.today/0AlZP
Part of it is "human in the loop" for write actions, part of it is commercial banks are deathly terrified of agents being able to move deposits around rapidly to maximize yield, as those deposits are cheap cost of capital banks use to lend against. Historically, deposits of unsophisticated financial services consumers were sticky, and that assumption is breaking down. Agents can be consumer copilots towards information asymmetry in this context.
"computah, maximize rate of return, minimize interest expenses, manage cashflow, make no mistakes."
Corporate Personhood in the agentic age.
Would be interesting to see what 2025 looked like in comparison.
The rate at which flaws are being found is just insane. Many people warned us in the past that our lax security postures would come back to bite us, and we're finally here.
Well, an economist would say, we have as much security as we collectively decided we were willing to pay for.
And theres really only one of 2 outcomes as this progresses as I can see it:
1) The AI's are well matched, and the outcome is balanced, and it ends up being a metric of the internet itself that gets monitored, like this website is doing.
or
2) It crashes in such a spectacular fashion that important utilities and industries are distrupted, with the length of time for recovery being the determining factor in how many people lose their minds, start looting, etc ... you know the story.
#1 depends on everyone deploying in a timely manner the fixes that the blue AIs find.
The bad guys are historically much better at keeping their systems current.
Collectively, billions have been spent on cybersecurity. It was just mostly wasted, that's all.
In every billion dollar company I've worked at, the infosec team has numbered less than 10 people.
Because we build things the wrong way.
"We take code and make it secure"
instead of
"We take secure and make it code".
That said, maybe it's impossible. Maybe turing completeness and security are antithetical and someone will always be able to find a way to poke a hole in the system from a lower layer of reality.
"We take secure and make it code".
Yeah, that. Manual controls w/ an optional automation, not just, automation with an optional "oh shit" button.
As for the AI's hacking and patching, one could reason since we are dealing with Turing machines that as long as changes to any given codebase/version cease, then all possible holes and patches would be found given enough attacks for that specific release.
Perhaps unfolding almost exactly like Conways 'Game of Life' with an order or two magnitude more rules and states, where the end pattern for any release is 'stability.'
We need a realtime dashboard for this :D
This may be a side conversation, but wondered how far away we are to a small LLM being prompted to turn itself into a worm that uses all exploits it knows, and prompts other LLM's when it has access.
I've seen this discussed on HN a few times under articles, and is a risk I've seen communicated in AI safety.
I guess it's being called an AI prompt worm. It's not quite to the stage of sovereign AI where the entire model weights are moved with the 'virus', but still presents a pretty big risk.
It’s orders of magnitude easier to destroy something than it is to build something up. It’s why bad leaders can be much more devastating than the best leaders.
That reminds me that I need to see if my copy of Nero Burning ROM still works.
A very cogent point indeed.
This will be a real test which societies start looting in such circumstances
I fortunately live in a peaceful, cooperative country of Poland that looks down upon such practices unlike us or France or uk
Let the best win. Over and out
Oh, don't worry, when all your European neighbors are busy fighting each other with sticks Russia will come along and start coveting what is yours.
Poland and Ukraine will hold the candle of civilisation together against all odds
I was curios if there was a noticable increase in the number of security incidents before 2026 - and the answer seems to be "no". The Identity Theft Resource Center has the following data for Reported Data Compromises in the US (keep in mind that the internet itself has been growing as well):
| Year | Reported US data compromises |
|---|---:|
| 2016 | 1,099 |
| 2017 | 1,506 |
| 2018 | 1,175 |
| 2019 | 1,279 |
| 2020 | 1,107 |
| 2021 | 1,859 |
| 2022 | 1,798 |
| 2023 | 3,202 |
| 2024 | 3,152 |
| 2025 | 3,322 |
Curios what 2026 will look like...
Sources:
https://www.idtheftcenter.org/wp-content/uploads/2022/04/ITR...
https://www.idtheftcenter.org/wp-content/uploads/2026/01/202...
Suddenly almost doubling in 2023 and staying there doesn’t strike you as a noticeable increase?
i will backfill historical data now!
the flaws you're seeing are the same that didn't convict donald trump on January 6th.
That's all. full stop. all this AI agent stuff is jazz hands. Large VC funded labs are just "more valuable" to the political establishment than anything else.
Every ai generated page tries to cram way too much information in way too small a place
I'm ok with that. Better than those 2007 iPhone bare pages where you can't do or read anything.
What I don't like is that every site now looks the same.
And also just useless or confusing information like the box labeled closed that has “Ongoing” inside.
Definitely. And often repeated/redundant information in many cases.
someone called it "narrative ui", usually opus and deepseek dont do it as much, this was grok bot cleaning up now
My eyes have no idea what to focus on.
It would be more readable if every AI-generated page didn't go for the dark-mode + glowing neon cyber aesthetic.
My biggest issue is the dark theme, which makes it more or less impossible to consume for people with astigmatism. I looked at the page half a minute ago and my eyes are still trying to recover fully.
i know, it's pissing me off too. fixing now!
I don't understand the categorization for incidents. This signal vulnerability[1] is listed as "Live" and "ongoing" but was patched over a month ago (just announced today). If an incident with no known exploits is "ongoing" 1.5 months after the patch is released, when would it be over?
[1] https://pwn.watch/i/signal-ringrtc-cve-2026-113380
After the first 8 hours of playing with Mythos, I was asked what I thought. My response, "this generation of LLMs is going to drive the largest wave of security incidents the world has ever seen."
It is still getting started.
Isn’t that true for every generation of LLMs?
The thing to watch is what the CCP will do once people start abusing Chinese model capabilities. I don't think China wants to be the face of widespread cyber destruction (and definitely not a victim of it), and it only takes a single unhinged asshole to ruin it for everyone.
Also the flip side where Chinese models are used to attack US infra, just loading artillery shells into the "Ban Chinese Models" cannon.
The rss button doesn't work, kicks back a 404 when you are redirected to https://pwn.watch/feed.xml :-(.
In fact, it seems to be the case for the "json" and "llms.txt" buttons, too.
Not surprising for an AI slope website. It looks great until you start clicking buttons and see that everything’s broken.
first of all it doesnt look great lmfao second of all it was made in like 15 mins and wasn't supposed to go viral here improving shit now
fixing rn txt!
The "sponsors" are just other random AI-generated websites by the same author.
lmfao no, one is my website (https://tinkerer.club) and two are actually startups of people who sponsor me @ https://kitze.io/sponsors :D
thanks for sharing!! i vibeslopped this in the middle of doing 1389418934 security tasks today out of panic. i will clean up the design and make it better :) i also made an x acccount if you wanna follow there: https://twitter.com/pwnwatch_app if you want to join our crazy group of self hosting dorks we are at https://tinkerer.club <3
That "copy instructions got agents" thing is a really great idea. I just used it :)
It would have been an ever better idea if I could figure out what it's for before copying :)
Yeah I had to paste it first to check it was safe
Great for a rapid response, but seems... not so secure?
I'd probably add the on-hold queue of Zone-H... and verified stuff from the past week. Maybe just the Special Defacement reports.
This is a nice website.
Was hunting for a real time graph of incidents and patches, like a stock market chart of the end of the software world, or the birth of artificial consciousness, depending on how squiggly the lines are.
Just the heatmap apparently. :|
Also, as all the humans are installing their "AI on every device" clustering software, the pace of it all should really pick up, and this reminds me of the following SFW movie clip:
"The suspense is terrible. I hope it will last." - Willy Wonka
https://www.youtube.com/watch?v=Oci1CuCht7E
A simple line chart would be more helpful, informative and humbling than a heat map.
I agree, I personally dont like the heatmap and find it very hard to read.
adding multiple charts now!
I agree, except for how it lets us see that AI agents increasingly don't mind working on the weekends
what a wonderful day october 21 has been
The bots love that whatever tailwind theme that is.
To be fair I also like that them. But many of these themes that used to be “oh this is a nice website” now make me go “oh AI generated!”
we've got to tell these agents to chill out on the density a little, this page could be more informative with half the data because it would be easier to ingest
Definitely wouldn't mind them switching up the theming too- the sites they generate all have the same default theming.
Cool but i am immediately averse to AI UI slop interfaces.
unslopping it right now!
Beautiful website, well done.
An over time graph with a rolling window of 7d and 28d would likely be a nice addition.
Great work!
this website is AI slop
Leftist?
> Ongoing security incidents, newest first: CVEs, what's affected, which versions fix it, and the advisories and posts behind each one.
For fucks sake. The author could have invested at least half an hour to replace this obvious LLM slop regurgitation of the prompt with something of their own.
"Buy sponsor slot for 149$/month", yeah, spotted the grift. For that level of payment it's at least reasonable to expect the design to be something else than the usual LLM garbage mixture of 30 different font styles.
i ended up in the hospital today for some virus sorry i didnt have time to perfectly polish this thing i made in 15 mins with grok bot lmfao
and fyi my sponsors are not only for this, they come from https://kitze.io/sponsors :D
AI slop site. At least change the fonts and don't use the stereotypical smelly AI aesthetic.
on ittttt, ironically i made https://flavors.design specifically for unslopping and i didn't even use it