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)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16