Hacker News new | ask | show | jobs
by lxgr 83 days ago
It works well so far, for you.

Are you confident it would still work against sophisticated prompt injection attacks that override your "strongly worded message"?

Strongly worded signs can be great for safety (actual mechanisms preventing undesirable actions from being taken are still much better), but are essentially meaningless for security.
2 comments
unshavedyak 83 days ago
Not sure about OPs impl, but the wording doesn’t matter. The hook prevents the use of whatever action you want. Eg it’s impossible for Claude to use Emojis for me. My hook doesn’t allow it.

So it’s deterministic based upon however the script it written

link
jmalicki 82 days ago
If your hook prevents rm, it is possible for Claude to write a script that does the rm and execute the script.
link
unshavedyak 81 days ago
Yup, that's totally possible, but you still have to approve the script. But that's a bit of a moot point right? Claude is writing code, nearly anything is possible with code, ergo claude could do anything lol.
link
esperent 83 days ago
I mean, that's like saying are you sure that your antivirus would prevent every possible virus? Are you sure that you haven't made some mistake in your dev box setup that would allow a hacker to compromise it? What if a thief broke i to your house and stole your laptop? That's happened to me before, much more annoying to recover from that an accidental rm rf.

I do my best to keep off site back ups and don't worry about what I can't control.

link
lxgr 83 days ago
> I mean, that's like saying are you sure that your antivirus would prevent every possible virus?

Yes, I'm saying it's pretty much as bad as antivirus software.

> Are you sure that you haven't made some mistake in your dev box setup that would allow a hacker to compromise it?

Different category of error: Heuristically derived deterministic protection vs. protection based on a stochastic process.

> much more annoying to recover from that an accidental rm rf.

My point is that it's a different category, not that one is on average worse than the other. You don't want your security to just stand against the median attacker.

link