moai-workflow-ddd
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill presents an inherent risk of indirect prompt injection as it ingests and processes untrusted data from external source code and project metadata.
- Ingestion points: The skill analyzes source code patterns, module dependencies, and test results from the project being refactored.
- Boundary markers: No specific delimiters or protective instructions are utilized to separate the external code data from the agent's internal operational logic.
- Capability inventory: The skill facilitates extensive capabilities including file system modification, version control operations, and the execution of various build and analysis tools via the shell.
- Sanitization: There are no mechanisms described for validating, escaping, or sanitizing the content of the codebase before it is processed by the agent.
Audit Metadata