create-package-skill

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill guides the agent through executing several shell commands for package analysis and validation. These include using grep and git diff to identify code patterns, python -c for import smoke tests, and azsdk_package_run_check for compliance validation. These are standard operations within the Azure SDK engineering environment.
  • [EXTERNAL_DOWNLOADS]: The documentation references @microsoft/vally-cli, an npm-based linting tool provided by Microsoft for skill validation. This is a trusted internal tool used to ensure the generated skills meet repository standards.
  • [SAFE]: The skill includes explicit security guardrails, instructing agents to never embed secrets in skill content and to never bypass established CI or gating tools like pylint or mypy.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 09:48 AM
Security Audit — agent-trust-hub — create-package-skill