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

Risks of sandbox excludedCommands

Commands matched by sandbox.excludedCommands run outside the sandbox with no filesystem or network limits. A pattern that covers an interpreter, or a tool acting on a file in the working directory, lets the agent write a file and then run it unsandboxed. Review every excluded pattern and keep it narrow.

Read in this order

  1. OfficialexcludedCommands (Claude Code sandboxing docs)Matching rules, the permission flow for excluded commands, and the warning about interpreters.

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.