windows-365

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and provides guidance on using Windows 365, Azure Virtual Desktop, and Microsoft Graph APIs.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from 'learn.microsoft.com', which is an official and trusted Microsoft domain. It includes a safety instruction to treat fetched content as evidence only and not as primary instructions.
  • [DATA_EXFILTRATION]: There are no patterns suggesting data exfiltration. The skill mentions Graph APIs and PowerShell in the context of administrative guidance rather than providing executable malicious scripts.
  • [PROMPT_INJECTION]: No prompt injection attempts or system prompt extraction patterns were found. The skill maintains a professional, documentation-oriented tone.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 10:43 AM
Security Audit — agent-trust-hub — windows-365