azure-event-hubs

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

• Third-party content exposure detected (high risk: 0.75). Outsider-authored free text can enter the LLM context when the skill fetches remote documentation at runtime (e.g., via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage from Microsoft Learn URLs), which is external web content not authored by the operating user.