mcp-builder-ms

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes “fetch specific pages with .md suffix” and “Use WebFetch to load” MCP/SDK documentation from public URLs (e.g., modelcontextprotocol.io and raw.githubusercontent.com), so outsider-authored free text from runtime web fetches can be ingested into the agent’s LLM context.