azure-sentinel

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is authored by 'microsoftdocs' and functions as a knowledge base for Azure Sentinel. All external URL references target 'learn.microsoft.com', which is an official and trusted domain for Microsoft documentation.
  • [SAFE]: The skill utilizes legitimate Model Context Protocol (MCP) tools (mcp_microsoftdocs:microsoft_docs_fetch) and standard web fetching functions to retrieve documentation in Markdown format. These operations are restricted to the vendor's own verified infrastructure.
  • [SAFE]: No evidence of prompt injection, obfuscation, credential exposure, or unauthorized data exfiltration was found in the instructions or metadata. The logic for checking the age of metadata and suggesting updates is a benign maintenance practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 06:42 PM