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 runtime fetching of external Markdown docs via the mcp_microsoftdocs:microsoft_docs_fetch tool or fetch_webpage (e.g. https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/prompt-flow-tools/prompt-tool), and those fetched documents are incorporated into the agent context and can directly affect prompts/instructions.