moai-cc-commands
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill establishes an indirect prompt injection surface through its command parameter patterns.
- Ingestion points: The
templates/command-template.mdfile defines input parameters (param1,param2) that ingest untrusted user data into the agent context. - Boundary markers: No delimiters or isolation instructions are provided to ensure the agent ignores instructions embedded within the parameter values.
- Capability inventory: The skill is configured with powerful tools including
Bash,Read, andGlobinSKILL.md, while the template referencesWriteandTask. - Sanitization: There are no mechanisms described for sanitizing or validating user input before processing.
- [PROMPT_INJECTION]: Inconsistent metadata was found, including conflicting version numbers (v4.0.0 vs v2.0.0) and discrepancies between the tools listed in the skill definition versus the command template.
Audit Metadata