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

Codex approval policies and sandbox modes

Codex separates the approval policy, which sets when it asks, from the sandbox mode, which sets what commands can touch. Policies include on-request, never and a granular option, and auto review can route eligible requests to a reviewer agent. Sandbox modes run from read-only through workspace-write to danger-full-access, which belongs only on isolated machines.

Read in this order

  1. OfficialCodex: Agent approvals and securityStart here: how approval policy and sandbox mode combine into real behavior.
  2. OfficialCodex: SandboxWhat each sandbox mode actually blocks on files and network.
  3. OfficialCodex: Auto-reviewHow the reviewer agent decides, so you can judge whether to trust it.

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.