mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to fetch and read public web pages (e.g., https://modelcontextprotocol.io/sitemap.xml and raw.githubusercontent.com/.../README.md) and to use that external documentation during Phase 1 planning and implementation, so untrusted third‑party content will be ingested and can materially influence tool design and subsequent agent actions.