microsoft-foundry-tools

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 documentation at runtime (via the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage tools) which would inject external content into the agent's context and thus directly influence prompts—for example, it fetches pages such as https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices.