fastmcp
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides code examples for building Model Context Protocol (MCP) servers. It includes security-positive recommendations, such as using environment variables (os.environ) instead of hardcoding API URLs and ensuring that middleware logs only argument keys rather than sensitive values to prevent credential leaking.
- [EXTERNAL_DOWNLOADS]: The skill references the official FastMCP repository (github.com/jlowin/fastmcp) and the httpx library for making network requests. These are well-known resources in the Python ecosystem and are used here for standard development purposes.
- [PROMPT_INJECTION]: The skill provides guidance on writing tool docstrings and prompts to guide agent behavior correctly. No attempts to override safety filters or bypass system instructions were detected.
- [COMMAND_EXECUTION]: No unauthorized or dangerous command execution patterns were found. Code examples use standard library functions and well-known testing frameworks like pytest.
Audit Metadata