Verdicts
Rules that evaluate prompts and return allow/block/warn.
no-secrets
blockRejects prompts containing AWS keys, GitHub tokens, or API credentials.
no-pii
warnChecks for SSN, credit card numbers, and other PII before processing.
budget-check
warnEstimates prompt cost and blocks if it exceeds configured threshold.
language-filter
blockAllows only configured languages, rejects others.
rate-limit
blockPer-user rate limiting based on API key or session.