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 macintux on Wednesday July 08, 2026 @05:51PM (#48837894)
> There will come a time when properly designed LLM apps are not vulnerable, and there will still be poorly designed apps that are.

Whether it’s possible to properly secure an LLM (and retain its utility) seems to be heavily disputed, in this thread and elsewhere.

[ Parent | on HN ]

There are no comments on this comment yet.