azure-content-safety

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly requires fetching remote Markdown docs at runtime (via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage) and will inject those learn.microsoft.com pages (e.g., https://learn.microsoft.com/en-us/azure/ai-services/content-safety/how-to/improve-performance) into the agent context to guide responses, so external content fetched during runtime can directly influence prompts/responses.