Safety and permissions

Required

• Run agents in a sandbox

  Required

  Run coding agents in an isolated environment, such as a container, a virtual machine or the agent's own sandbox mode.

• Keep production credentials away from agents

  Required

  Never give a coding agent production keys, database passwords or customer data.

• Give agents the fewest rights they need

  Required

  Give each agent token only the rights its task needs, and make it short-lived and easy to revoke.

• Approve destructive commands

  Required

  Require a person's approval before an agent deletes data, rewrites history, changes infrastructure or spends money.

• Treat what the agent reads as untrusted

  Required

  Assume any web page, issue, file, dependency or tool result an agent reads may contain instructions meant to hijack it.

• Review agent settings like code

  Required

  Treat instruction files, agent settings, hooks and rule folders as code that can run. Review every change to them and scan them for hidden text.

• Open unknown repositories in a sandbox

  Required

  Open a repository you did not write in a container or virtual machine first. Trust it in your editor or agent only after reading its config.

Recommended

• Know what the agent tool does with your code

  Recommended

  Before an agent reads your code, check whether its provider stores it, for how long, and whether it trains models on it.