mcp-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs agents to fetch and read public web content (e.g., "https://modelcontextprotocol.io/sitemap.xml", "https://raw.githubusercontent.com/modelcontextprotocol/.../README.md" and "use web search and WebFetch as needed") so the agent will ingest open/public third‑party pages (including raw GitHub content) as part of its workflow, exposing it to untrusted, user‑provided content that could carry indirect prompt injection.