mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to fetch and read public web documents (e.g., Phase 1.3 "Use WebFetch to load: https://modelcontextprotocol.io/llms-full.txt", Phase 1.4's raw.githubusercontent.com SDK READMEs, and "use web search and the WebFetch tool as needed"), so it ingests untrusted public third‑party content that the agent is expected to interpret and that can materially influence tool design and subsequent actions.