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

OS sandboxes for agent commands

A sandbox enforces limits in the operating system, so they hold even when the model is fooled. Agents now use Seatbelt on macOS and bubblewrap, Landlock and seccomp on Linux to restrict file writes and network access for every command they spawn. Sandboxing also cuts approval prompts, which removes much of the pressure to switch to unsafe modes.

Read in this order

  1. ArticleMaking Claude Code safer with sandboxing (Anthropic)Start here: why sandboxing cuts prompts and how the design works.
  2. OfficialClaude Code: Configure the sandboxed Bash toolThe settings that turn on filesystem and network limits for Bash.
  3. OfficialCodex: SandboxCodex's sandbox for comparison, including its modes and defaults.

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.