microsoft-foundry-classic

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 external Microsoft Learn documentation at runtime (e.g., https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/safety-system-message-templates) via mcp_microsoftdocs or fetch_webpage, and that fetched Markdown can be injected as system message templates or instructions that directly control agent prompts, making it a required runtime dependency.