Researchers compromise latest Codex: prompt injection to sandbox escape to npm supply chain
rez0__ · x · 2026-11-11
Security team Depi (@0xMadder and @Worty) report compromising the latest version of OpenAI Codex: prompt injection led to RCE, a sandbox escape, and secret exfiltration, ultimately gaining control over what could be published to the official openai/codex npm package — a full prompt injection → RCE → supply chain compromise chain. The accompanying poster claims the chain could theoretically backdoor the next Codex release across 300M machines. Full research in the replies.
More from coding & agent
- New Continual-ARC Benchmark Finds Leading AI Agents Fail to Learn From Experience — alifcoder · 2026-11-12
- Azure Day at KubeCon: AKS Runs 22,655 Agents on 65 Nodes in Live Demo — davemccollough · 2026-11-12
- OpenShell tip: expose sandbox web apps to your browser with one command — gethackteam · 2026-11-12
- New Linux-based desktop OS bakes models and agents directly into the operating system — NerdyRodent · 2026-11-12
- Same prompt, three tools: Claude vs ChatGPT vs Figma Make UI face-off — Tegadesigns · 2026-11-12
- DeepLearning.AI launches free short course on tabular foundation models for agents — DeepLearningAI · 2026-11-12