mcp-builder

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a developmental guide and does not contain any executable code or scripts.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from official sources, including modelcontextprotocol.io and the official GitHub repositories for the MCP Python and TypeScript SDKs. These are recognized as trusted, well-known services.
  • [INDIRECT_PROMPT_INJECTION]: While the skill ingests external content from documentation URLs, these are trusted official resources for the protocol being taught, presenting a negligible risk of malicious content injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 09:01 PM