moai-baas-clerk-ext

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8).
  • Ingestion points: The skill utilizes mcp__context7__get-library-docs to retrieve external library documentation at runtime.
  • Boundary markers: There are no explicit delimiters or system instructions present to ensure the agent ignores potentially malicious instructions embedded within the retrieved documentation.
  • Capability inventory: The skill is granted access to high-privilege tools including Bash, Write, and Edit, which could be exploited by malicious content processed from external sources.
  • Sanitization: No evidence of validation or filtering for the data returned from the documentation retrieval tools is defined.
  • [DATA_EXFILTRATION]: The skill communicates with the official Clerk API (api.clerk.dev) to manage organization invitations and user management operations. These network operations target a well-known authentication service and are considered safe functional components.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 01:06 AM