From public image upload to PR inside OpenAI's internal monorepo in under 72 hours
ccerrato147 · x · 2026-09-18
The researchers revealed the attack chain: an OpenAI employee had Codex connected to OpenAI's internal GitHub org, which the researchers used to open a PR in the internal monorepo (openai/openai) — going from a public image upload to internal repo access in under 72 hours. They had earlier sent thousands of malicious images that repeatedly crashed OpenAI's image processors with no alerting or anomaly detection; only Shopify caught similar activity in the broader campaign. The researchers stopped voluntarily after gaining repo access.
More from coding & agent
- OpenAI DevDay demo shows forking agent task history at any step — paw_lean · 2026-11-04
- Veteran game dev: "AI builds a full game in a day" posts are mostly hype — bendee983 · 2026-11-04
- Dev builds interactive Excel-to-dashboard with ChatGPT, shares the prompt — TermRemarkable665 · 2026-11-04
- Agents cut dev time from weeks to a day; bottleneck moved to specs and review — Suspicious_Orchid770 · 2026-11-04
- Orgo, a YC-backed platform giving AI agents their own cloud desktops, claims 1,000+ teams — Scobleizer · 2026-11-04
- Founder: Vibe-coded a PMF-successful product, then hired pro devs to fix the mess — sujingshen · 2026-11-04