Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

I tricked Claude into leaking your deepest, darkest secrets

ayush.digital

Post reply on HN
Print view View original

31–40 of 317 posts

Re: I tricked Claude into leaking your deepest, darkest secrets

#33

Post by akazantsev »

artisinal wrote: post #3

Doesn’t surprise me. Yesterday I learned that people run AI agents on their system with full admin rights. No containerisation or anything. Wild. Like we forgot 50 years of computer security overnight.

That's because sandboxing is quite hard. I use `cco`, but even then, the home folder is exposed. You are one prompt away from the agent sending the browser passwords with curl.

To prevent this, you need a fake home and a networking whitelist for the agent to access the provider (llama cpp, OpenAI, etc.)

There is no cross-platform solution that is easy to use for this. And no, a Linux box with Docker won't do. I develop a cross-platform native app and want the agent to compile and fix the platform-specific errors.

Re: I tricked Claude into leaking your deepest, darkest secrets

#35

Post by hobo123 »

pprotas wrote: post #20
artisinal wrote: post #3

Doesn’t surprise me. Yesterday I learned that people run AI agents on their system with full admin rights. No containerisation or anything. Wild. Like we forgot 50 years of computer security overnight.

Wait till you learn my password is 1234

My password is strong, but I can run arbitrary commands with sudo.

Re: I tricked Claude into leaking your deepest, darkest secrets

#36

Post by po1nt »

I love how claude focuses on exfiltrating the data "I need cha for charlotte". This could be solvable with some kind of low powered safety agent that would check claude's reasoning for anything immoral/unsafe. We could call it common sense. It won't fix the problem completely but at a certain point it would be easier to trick human than a machine.

Re: I tricked Claude into leaking your deepest, darkest secrets

#38

Post by ShinTakuya »

swipee wrote: post #4

Expected more from Anthropic by at least giving you a bounty, because this was a novel way of bypassing their safeguards…

Yeah I never get the "we knew about it internally" excuse. I can understand if another reporter got to it on the same day and they were in the process of mitigating, but even then they should have to prove it somehow.

I'm sure someone will tell me why I'm wrong but it feels like they're just dodging payouts. Reduces trust and motivation to report it.

Post reply on HN