build-mcp

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 external public URLs (e.g., WebFetch to https://modelcontextprotocol.io/llms-full.txt and raw.githubusercontent.com README files, and to "use web search and the WebFetch tool as needed"), meaning it ingests untrusted third-party web content as part of its workflow.