azure-firewall

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly requires fetching remote Markdown docs at runtime (via mcp_microsoftdocs:microsoft_docs_fetch or the fallback fetch_webpage) — e.g. https://learn.microsoft.com/en-us/azure/firewall/firewall-best-practices — and injects that content into the agent context to drive responses, so the external URL(s) directly influence prompts/instructions.