mcp-builder
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches protocol documentation and SDK specifications from the official Model Context Protocol domain (modelcontextprotocol.io) and its associated GitHub repositories to provide accurate development guidance.- [COMMAND_EXECUTION]: The skill provides instructions for building projects (npm run build) and running server evaluations (python scripts/evaluation.py) which are standard operations for a developer tool.- [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for potentially untrusted data by fetching external documentation and processing outputs from live MCP server tools during research and evaluation phases.- [DYNAMIC_EXECUTION]: The included evaluation harness (scripts/evaluation.py) dynamically invokes and interacts with tools from the MCP server being tested, which is the intended core functionality of the development environment.
Audit Metadata