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

Allowlists and deny rules

Permission rules pre-approve safe actions and block dangerous ones, such as reading .env files, running curl or calling a particular MCP tool. They cut prompt fatigue, but allowlisted commands can be abused through argument injection, so rules work best inside a sandbox rather than instead of one. Keep deny rules for secrets and destructive commands in a centrally managed file.

Read in this order

  1. OfficialClaude Code: Configure permissionsStart here: a full worked rule system with allow, ask and deny tiers.
  2. ArticlePrompt injection to RCE in AI agents (Trail of Bits)Shows how allowlisted commands still led to remote code execution.
  3. OfficialGemini CLI: Policy engineA different rule engine, useful for comparing syntax and precedence.

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.