azure-bastion

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

• Potentially malicious external URL detected (high risk: 0.80). This skill explicitly requires fetching remote Markdown at runtime via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage and injecting that content into the agent context (e.g., https://learn.microsoft.com/en-us/azure/bastion/troubleshoot), so the fetched external document can directly control prompts/instructions.