News for hackers. Stuff that matters.

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

Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by amaze_28 on Wednesday July 08, 2026 @01:30PM (#48834730)
the most interesting part here isn't prompt injection worked, it's why the agent had read access to private repo at all while triaging a public issue.

an agent responding to public issue should only ever see context limited to that repo.

it seems like with the evolution of AI - we are slowly missing out basic security practices.

[ Parent | on HN ]
Re:GitLost: We Tricked GitHub's AI Agent into Leaking Privat... by pqdbr on Wednesday July 08, 2026 @01:41PM (#48834871)
Agreed, hard enforced by code. Surprised to see many comments here finding it reasonable that the agent could reply with private repo information on a question posted on a public repo, which IMHO is obviously a bug.
[ Parent | on HN ]