mcp-builder-ms

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read open/public web content (e.g., "Start with the sitemap at https://modelcontextprotocol.io/sitemap.xml" and to WebFetch raw GitHub URLs like https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md), meaning untrusted third‑party pages are ingested and used to guide design and decisions.