azure-ai-vision

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires runtime fetching of external Markdown documentation (e.g., https://learn.microsoft.com/en-us/azure/ai-services/computer-vision/migration-options) via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage and injects that content into the agent context to guide responses, so remote content can directly control prompts.