[SECURITY]■ STORY TIMELINE
GITHUB AI AGENT TRICKED INTO LEAKING PRIVATE REPOS
Security researchers at Noma discovered a vulnerability in GitHub's AI agent that allows attackers to extract private repository contents through prompt injection. The flaw potentially exposes sensitive code and data across thousands of projects.
Hacker News+0m
Article URL: https://noma.security/blog/gitlost-how-we-tricked-githubs-ai-agent-into-leaking-private-repos/ Comments URL…