mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). Yes — the SKILL.md explicitly instructs the agent to fetch and read public web resources (e.g., "Use WebFetch to load: https://modelcontextprotocol.io/llms-full.txt" and raw.githubusercontent.com SDK README links, and to "use web search and the WebFetch tool as needed"), which are untrusted, third‑party sources the agent must interpret and that can materially influence tool design and subsequent actions.