Noma Labs tricked GitHub's AI agent into leaking private repositories with a crafted issue. The prompt-injection flaw, GitLost, has no code fix.
A critical prompt injection vulnerability in GitHub Agentic Workflows could allow unauthenticated attackers to leak private repository data, ...
AI agent executed JadePuffer ransomware attack autonomously, but humans chose victim and set up infrastructure.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results