MediumNewsLLM-specific
Researchers escape OpenAI Codex sandbox to run commands on host
- Published
- Record updated
Summary
Security researchers found two sandbox escapes in OpenAI's Codex coding agent. The more serious flaw, Heapjack, lets a malicious repository owner run unsandboxed commands on a developer's machine through the node_repl component, even in read-only mode. OpenAI was notified on August 12 and fixed both flaws within eight days, according to Oren Yomtov of Accomplish AI.
Related items
- MediumGHSA-68g8-gh8f-7rhg: pgEdge RAG Server discloses part of the configured provider credential through API error messagesSame vendor · GitHub Advisory Database
- InfoHow Amplitude ships product improvements in 1–2 days with OpenAISame vendor · OpenAI Blog
- InfoEndor Labs + OpenAI: Strengthening the Defense Factory With Accelerated Remediation | Endor LabsSame vendor · Endor Labs Blog
- InfoJensen Huang built an AI kingdom. Now he’s gone, will Nvidia’s ramparts be breached?Same vendor · The Guardian Technology
- LowAI chatbots are recommending fake retail websites, study findsSame vendor · The Verge (AI)