News for hackers. Stuff that matters.

A comment on GitLost: We Tricked GitHub's AI Agent into Leaking Private Repos. Parent comment

Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by catoc on Wednesday July 08, 2026 @11:36AM (#48833359)
Exactly!

Attempting to handle prompt injections by prompting the model (not to leak sensitive data), is like attempting to stop a fire by burning the area around it

[ Parent | on HN ]
Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by politician on Wednesday July 08, 2026 @11:51AM (#48833530)
My guy, that's actually how fires are stopped.

https://en.wikipedia.org/wiki/Firebreak

https://en.wikipedia.org/wiki/Controlled_burn

[ Parent | on HN ]
Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by catoc on Wednesday July 08, 2026 @11:58AM (#48833622)
Haha, nice. TIL.

So all we need is ‘controlled prompting’ to handle prompt injections :-)

[ Parent | on HN ]
Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by NateEag on Wednesday July 08, 2026 @04:19PM (#48836928)
It's maybe closer to putting a sign saying "The door is locked" on an unlocked bank vault.

It does nothing to improve security, and if someone manages to get inside and see the sign (i.e. "extract the prompt"), it gives them a strong hint there's interesting stuff behind this door.

[ Parent | on HN ]