clerk-auth
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill monitors for specific error strings from the user's environment to trigger assistance, which represents an ingestion surface for untrusted data. Evidence: 1. Ingestion points: 'Error Messages' triggers in README.md. 2. Boundary markers: Absent. 3. Capability inventory: No executable code provided in this file. 4. Sanitization: Absent.
- [SAFE] (SAFE): The README.md content is purely informational and contains no malicious code, obfuscation, or sensitive data exfiltration patterns. Test credentials mentioned (OTP 424242) are documented official Clerk testing defaults.
Audit Metadata