mcp-builder

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to fetch and read open/public third‑party web content (e.g., Phase 1.2: "Start with the sitemap at https://modelcontextprotocol.io/sitemap.xml" and "Use WebFetch to load https://raw.githubusercontent.com/.../README.md"), which the agent is expected to read and use to plan and implement tools—allowing untrusted, user-generated or public content to materially influence subsequent tool use and decisions.