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-docsto 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, andEdit, 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