mcp-builder

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation and SDK READMEs from the official Model Context Protocol GitHub organization and website to ensure implementation accuracy.
  • [COMMAND_EXECUTION]: Includes an evaluation harness (scripts/evaluation.py) that executes local commands or scripts provided by the user to launch and test MCP server implementations. This is a functional requirement for the developer-focused workflow.
  • [SAFE]: The skill provides high-quality security documentation in reference/mcp_best_practices.md, emphasizing OAuth 2.1, secret management via environment variables, DNS rebinding protection, and input sanitization to prevent directory traversal and command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:55 AM
Security Audit — agent-trust-hub — mcp-builder