microsoft-ai-platform-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- Command and Script Execution: The skill utilizes an internal Python script (
scripts/effort_profile_chart.py) to generate visualization charts via a code interpreter. - This script uses
matplotlibfor data visualization based on user inputs collected during the interview. - The execution is constrained to the platform's native code execution environment and does not involve external network requests or file system access beyond the generated chart image.
- User Data Ingestion: The skill collects project-specific information (project name, data sources, etc.) to provide recommendations.
- The data is used exclusively for scoring complexity and risk and is not transmitted to external services.
- Trusted Platform Context: The skill is designed for the Copilot Studio platform and adheres to its security model, including optional code interpreter permissions that must be explicitly enabled by an administrator.
Audit Metadata