Frequency
1
occurrences
First Seen
July 12, 2026
Last Seen
July 12, 2026
Related Threat Clusters
-
Ghostcommit Attack Exploits AI Reviewers to Steal Secrets
Researchers from the ASSET Research Group demonstrated a new attack method called 'Ghostcommit' that hides malicious instructions within PNG images to bypass AI code reviewers. The attack exploits a significant gap in…
9 articles · Updated July 11, 2026
Recent Intelligence Reports
- Researchers hid a prompt injection inside a PNG, and AI fell for it — Ground.News · July 12, 2026