moai-baas-clerk-ext
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Detected an indirect prompt injection surface. Evidence: 1. Ingestion points: Data is retrieved from external sources via WebFetch and Context7 documentation tools. 2. Boundary markers: Absent in the provided code templates. 3. Capability inventory: The skill has access to Bash, Write, and Edit tools. 4. Sanitization: No sanitization logic for external content is demonstrated.
- [EXTERNAL_DOWNLOADS]: Fetches configuration and patterns from official Clerk (clerk.dev) and Context7 resources, which are well-known and reputable.
- [CREDENTIALS_UNSAFE]: Code examples correctly use environment variables for sensitive keys, adhering to security best practices.
- [COMMAND_EXECUTION]: The skill is authorized to use Bash for project setup and management, but no malicious command patterns were found.
Audit Metadata