playwright-pro
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate testing toolkit with no malicious components. It uses authoritative instructions for its internal reasoning framework (Galyarder Framework) but does not attempt to bypass agent safety constraints.
- [SAFE]: Secret management for TestRail and BrowserStack integrations is handled correctly via environment variables (TESTRAIL_API_KEY, BROWSERSTACK_ACCESS_KEY) rather than hardcoded credentials.
- [SAFE]: Shell scripts included in the hooks/ directory are for utility purposes, such as project detection and code quality validation, and do not perform any dangerous operations.
- [SAFE]: Permission settings in settings.json are appropriately scoped to allow the execution of Playwright and TypeScript scripts necessary for the skill's functionality.
- [SAFE]: External communication is directed to well-known and user-configured services (BrowserStack and TestRail), following standard API integration patterns.
Audit Metadata