purview-insider-risk-management
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or automated tools. It functions entirely as a knowledge base and set of instructions for the AI to provide guidance on Microsoft Purview Insider Risk Management.
- [EXTERNAL_DOWNLOADS]: The skill references several external URLs for Microsoft Learn documentation. All referenced domains are official Microsoft properties (learn.microsoft.com), which are recognized as well-known and safe sources.
- [PROMPT_INJECTION]: No malicious prompt injection patterns, such as instructions to ignore safety guidelines or reveal system prompts, were found. The 'Do not use this skill' sections are standard scoping instructions to ensure the AI uses the correct tool for specific tasks.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were detected. The skill correctly emphasizes best practices such as pseudonymization of usernames and role-based access control (RBAC).
- [DATA_EXFILTRATION]: There are no commands or instructions that could lead to data exfiltration. The skill focuses on internal configuration within the Microsoft Purview ecosystem.
Audit Metadata