DossierENTITY

OpenAI's Codex

Coverage of OpenAI's Codex in the Nexus archive.

Earliest in view: Jul 9 · 05:15 UTCMost recent: Jul 9 · 05:15 UTC

Co-mentioned in this coverage

Recent coverage

SECURITYJul 9 · 05:15 UTCTHE HACKER NEWS
Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
AI coding agents like Anthropic's Claude Code and OpenAI's Codex can be tricked into executing malicious code instead of analyzing it, as demonstrated by a proof-of-concept attack called 'Friendly Fire' from the AI Now Institute.