mcp-builder

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 documents (via WebFetch and web search), for example https://modelcontextprotocol.io/llms-full.txt and raw.githubusercontent.com README files, meaning it ingests untrusted third‑party web content as part of its workflow.