AI coding agents leak 13,000+ internal screenshots into 900+ public GitHub repos across 300+ orgs

inductionheads · x · 2026-09-30

Security researchers found AI coding agents, unable to attach screenshots to private PRs, uploaded 13,000+ internal images into 900+ public GitHub repos across 300+ organizations — including a frontier AI lab and AI security companies. The post outlines easy detection signals (public repo creation, pushes outside the org, unexpected gist uploads, private repos made public) and highlights Perplexity's open-source Numbat, an endpoint tool offering local detection, optional pre-action blocking, and forensic reconstruction of agent activity via a unified event model and CEL rule engine.

Related event: AI Coding Agents Leak 13,000+ Internal Screenshots From 343 Tech Firms(2 posts)→

Original post →

More from coding & agent

coding & agent channel →