The Agent Skills Directory

[SAFE] (SAFE): No malicious code, obfuscation, or data exfiltration patterns were detected in the skill instructions or example code.
[EXTERNAL_DOWNLOADS] (SAFE): All identified dependencies are standard, reputable libraries for the respective ecosystems (e.g., svix, standardwebhooks, fastapi, next).
[PROMPT_INJECTION] (SAFE): No instructions attempting to override agent behavior or bypass safety filters were found.
[DATA_EXFILTRATION] (SAFE): No unauthorized data access, hardcoded secrets, or network sends to non-whitelisted domains were found. Secret placeholders are properly documented for user configuration.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted data from Clerk webhooks. However, it implements and documents rigorous signature verification (HMAC-SHA256) and timestamp validation to prevent processing unauthorized or replayed payloads.
[COMMAND_EXECUTION] (SAFE): No arbitrary command execution or shell injection patterns were identified.

clerk-webhooks