mcp-builder

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the developer/agent to fetch and load public web content (e.g., "https://modelcontextprotocol.io/sitemap.xml" and "https://raw.githubusercontent.com/.../README.md", and "use web search and WebFetch as needed" in Phase 1 and the Evaluation Guide), which are open/public, potentially user-generated sources that the agent is expected to read and use to plan tool design and evaluation—meaning external content can materially influence tool choices and next actions and thus could enable indirect prompt injection.