azure-speech

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires fetching remote Markdown docs at runtime (e.g., https://learn.microsoft.com/en-us/azure/ai-services/speech-service/faq-tts) via the mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage fallback and injecting that content into the agent context, which can directly control prompts/responses.