mcp-developer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No indicators of credential theft, data exfiltration, or unauthorized command execution found in the skill definitions.
- [Indirect Prompt Injection] (LOW): The skill is designed to ingest and analyze user-provided source code files (.ts, .js, .jsx, .tsx). This creates an attack surface where malicious instructions could be embedded in the code files being reviewed.
- Ingestion points: Source code files processed during the 'Review' and 'Diagnosis' phases defined in SKILL.md.
- Boundary markers: Absent; the skill lacks explicit delimiters to separate user code from instructions.
- Capability inventory: Limited to providing textual analysis, advice, and regex-based validation feedback. No script execution or file-writing capabilities detected.
- Sanitization: Absent; the skill relies on the LLM's base safety filters for processing input code.
Audit Metadata