By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

OpenAI Codex

Codex is OpenAI's coding agent, available as a CLI, an IDE extension, inside the ChatGPT apps, and as a cloud service. It separates the sandbox, which sets what commands can technically touch, from the approval policy, which sets when it must stop and ask. Optional auto-review, rules and managed configuration cover organizations.

Read in this order

  1. OfficialAgent approvals and security (Codex docs)Start here: how sandbox and approval policy combine, and the default posture.
  2. OfficialSandbox (Codex docs)What the sandbox actually blocks for files and network access.
  3. ArticleRunning Codex safely at OpenAIHow OpenAI runs Codex internally, a real-world example of the controls in use.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.