microsoft-ai-platform-advisor

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [Command Execution]: The skill uses the Copilot Studio code interpreter to execute a local Python script (scripts/effort_profile_chart.py). This is used to render a PNG quadrant chart based on user inputs from the discovery interview. This behavior is triggered by the agent at the end of the analysis phase.
  • [Dynamic Execution]: The skill incorporates a Python script that uses matplotlib to generate charts. While this involves running code at runtime, the script is static, bundled with the skill, and its inputs (project name, scores) are strictly derived from the preceding user interview. This is a standard pattern for data visualization in AI agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 11:55 PM
Security Audit — agent-trust-hub — microsoft-ai-platform-advisor