clerk-auth
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill file is composed strictly of markdown text describing architectural patterns. There are no scripts (.js, .py, .sh) or command-line instructions provided that could be executed by an agent.
- [DATA_EXFILTRATION] (SAFE): There are no patterns involving access to sensitive local files (e.g., .env, .ssh) or outbound network requests.
- [PROMPT_INJECTION] (SAFE): The text focuses on technical implementation details and does not contain instructions designed to override the agent's system prompt or bypass safety guardrails.
- [EXTERNAL_DOWNLOADS] (SAFE): No package manager commands (npm, pip) or remote script fetching (curl, wget) were detected.
- [METADATA_POISONING] (LOW): The 'Sharp Edges' section contains placeholder text ('Issue', 'See docs'), which is non-functional and likely indicates an incomplete template, but presents no security risk.
Audit Metadata