HomeAI · summaries
Storia in 5 fonti
'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets
A PNG hiding a prompt injection could steal your repo's secrets, researchers demonstrate. The technique, dubbed 'Ghostcommit,' slipped past AI code reviewers CodeRabbit and Bugbot, which never open image files at all, then convinced a coding agent to read a repo's .env and write every secret into the code as a list of numbers.
Confronto fonti
5 prospettive sulla stessa storiaTimeline cronologica
- ·
thenextweb.com
GitLost: GitHub's AI agent leaks private repos when asked
Noma Labs tricked GitHub's AI agent into leaking private repositories with a crafted issue. The prompt-injection flaw, GitLost, has no code fix.
- ·
thehackernews.com
GhostApproval Symlink Flaws Could Let Malicious Repos Run Code in AI Coding Agents
Wiz says GhostApproval abuses symlinks so AI coding agents write to SSH keys or shell startup files while showing benign paths.
