New GhostCommit Technique Hides Exploits in Images to Evade AI Code Reviewers

Researchers have revealed a technique called “GhostCommit,” which involves prompt injection by hiding malicious instructions within images included in pull requests. This technique has the potential to bypass text-only AI code reviewers and later manipulate coding agents into exposing repository secrets. The ASSET Research Group explained that this technique leverages the widening gap between automated […]

The post .