mcp-builder
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an instructional guide for creating MCP servers. It does not perform any automated actions, exfiltrate data, or attempt to bypass security controls.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from the official Model Context Protocol website and its verified GitHub repositories (modelcontextprotocol.io and github.com/modelcontextprotocol). These are well-known, trusted resources used for documentation purposes.
- [COMMAND_EXECUTION]: The instructions include standard development commands for building and testing software, such as 'npm run build' and 'python -m py_compile'. It recommends the use of 'timeout' and 'tmux' for safe execution of server processes, which is a defensive best practice.
- [DATA_EXFILTRATION]: No patterns of sensitive data access or exfiltration were found. The skill emphasizes building tools that respect context window limits and provide high-signal information.
- [PROMPT_INJECTION]: There are no instructions that attempt to override the AI's system prompt or bypass safety filters.
Audit Metadata