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's workflow explicitly instructs the agent to fetch and read public web pages (e.g., https://modelcontextprotocol.io/sitemap.xml and markdown pages like https://modelcontextprotocol.io/specification/draft.md, plus raw GitHub URLs such as https://raw.githubusercontent.com/modelcontextprotocol/typescript-sdk/main/README.md), which are untrusted third-party sources and are meant to be read and used to guide implementation and decisions—exposing the agent to potential indirect prompt injection.