azure-content-understanding

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

• Third-party content exposure detected (low risk: 0.10). The skill’s runtime can fetch remote documentation text (first-party Microsoft docs) via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage based on predefined queries/URLs, but it does not ingest outsider-authored free text from user/third-party submissions through a queue/feed it monitors.