purview-agent-365-security
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of educational instructions and architectural guidance for securing AI agents. No executable scripts or automation routines are present.
- [SAFE]: All external references target official documentation at
learn.microsoft.com, which is a well-known and trusted domain for technical information. - [SAFE]: No patterns of prompt injection, data exfiltration, or obfuscation were detected during the analysis.
Audit Metadata