entra-permissions-management
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely composed of Markdown documentation and instructional text. No executable scripts, binaries, or configuration files are included.
- [EXTERNAL_DOWNLOADS]: The skill includes several links to official Microsoft Learn documentation (learn.microsoft.com). These are trusted resources and do not involve the execution of remote code or the downloading of suspicious packages.
- [PROMPT_INJECTION]: There are no patterns suggesting an attempt to bypass agent safety filters or override system instructions. The 'DO NOT USE' warnings are legitimate scoping instructions for the user.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or sensitive credentials were found. The skill correctly recommends using on-demand permission grants rather than standing access.
- [DATA_EXFILTRATION]: No network-enabled tools or commands (such as curl or wget) are present. There is no logic for reading local sensitive files and sending them to external destinations.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or privilege escalation attempts (sudo, chmod) are included in the skill.
Audit Metadata