skills/microsoft/hve-core/rpi-review/Gen Agent Trust Hub

rpi-review

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution for Validation: The skill is designed to discover and run project-specific validation commands (e.g., package.json scripts, pytest, ruff) to verify code changes.
  • This behavior is restricted to verifying changed files within the project scope as part of the intended review workflow.
  • File System Interaction: The skill creates and updates review artifacts within a dedicated .copilot-tracking/ directory.
  • This practice ensures that internal tracking data is isolated from the primary source code and provides a clear audit trail of validation activities.
  • Least Privilege and Subagent Use: The skill prefers using specialized subagents (RPI Validator, Implementation Validator) for isolated validation tasks, reducing the risk of broad, unconstrained execution context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 03:39 PM
Security Audit — agent-trust-hub — rpi-review