azure-sentinel

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

• Potentially malicious external URL detected (high risk: 0.70). The skill requires runtime fetching of remote Markdown documentation (via mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage) from learn.microsoft.com (e.g. https://learn.microsoft.com/en-us/azure/sentinel/datalake/sentinel-mcp-get-started), and that fetched content is injected into the agent context to guide its responses, so it can directly control prompts.