mcp-builder

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

• Third-party content exposure detected (high risk: 0.80). The guide explicitly instructs the agent to fetch and read public web resources (e.g., https://modelcontextprotocol.io/sitemap.xml and raw GitHub URLs such as https://raw.githubusercontent.com/modelcontextprotocol/python-sdk/main/README.md) and to "use web search and web fetch as needed" during documentation inspection and evaluation, which exposes it to untrusted third‑party content the agent will read and interpret.