Fail-closed Cedar policy gate + signed receipts for AI agent tool calls. Blocks what breaks the rules before it runs, denies on any policy error, and proves the gate is live with a startup self-test.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
Fail-closed Cedar policy gate + signed receipts for AI agent tool calls. Blocks what breaks the rules before it runs, denies on any policy error, and proves the gate is live with a startup self-test.