azure-microsoft-discovery

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

• Third-party content exposure detected (high risk: 0.85). The required workflow fetches remote documentation at runtime (public Microsoft Learn pages) via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage, and the returned Markdown is ingested into the agent’s LLM context, which is outsider-authored free text.