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. [...]
← Back to news
cybersecurity
'Ghostcommit' hides prompt injection in images to fool AI agents, steal secrets
Log in to like articles and leave feedback.
Log in with Telegram →