OpenAI Codex Launches Automated Security Review for GitHub PRs
nickbaumann_ · x · 2026-08-07
OpenAI has integrated a security review feature for Codex within GitHub. By commenting @codex security review on a PR, Codex automatically checks the diff, repo context, and threat model, then posts its security findings directly on the PR.
The feature is currently available as a research preview for Pro, Business, Enterprise, and Edu users, but is not yet available for Plus subscribers.
Related event: OpenAI Introduces Codex Security Review for GitHub PRs(4 posts)→
More from coding & agent
- Coding agent runs are getting long — one dev suggests breathing, not parallel sessions — teropa · 2026-10-16
- Dev builds MCP layer so Claude Code can work on servers without ever holding SSH keys — NETMESAFE · 2026-10-16
- As coding agents run longer autonomously, one dev's tip: don't parallel-session, just breathe — teropa · 2026-10-16
- 'Refusing to code with AI in 2026 is like refusing Google in 2005' — prasenx · 2026-10-16
- Claude Code adds idle compaction to save 1h prompt cache on idle sessions — EricBuess · 2026-10-16
- Handling agents that crash mid-task: the hard part is the unknown outcome across the network — Responsible-Dare5139 · 2026-10-16