mcp-builder-ms

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs runtime fetching/loading of external markdown documentation (e.g., https://modelcontextprotocol.io/sitemap.xml, https://modelcontextprotocol.io/specification/draft.md, https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md, https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md), which would inject external instructions into the agent context and thus directly influence prompts/behavior.