playwright-pro
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to perform a variety of administrative and testing tasks. These include project scaffolding (npm init playwright), installing framework binaries (npx playwright install), running test suites (npx playwright test), and executing internal scripts for environment detection and test validation (detect-playwright.sh,validate-test.sh). - [EXTERNAL_DOWNLOADS]: The toolkit automates the installation of the Playwright framework and several Node.js dependencies from the official npm registry, such as
@playwright/test,otplib, and@axe-core/playwright. These are well-known libraries required for the skill's stated functionality. - [DATA_EXFILTRATION]: The reporting functionality allows for sending test results to external services like Slack via
curl. These operations use user-defined environment variables (SLACK_WEBHOOK_URL) and target established service providers, consistent with legitimate CI/CD notification patterns. - [CREDENTIALS_UNSAFE]: The skill manages integration credentials for TestRail and BrowserStack. It avoids hardcoded secrets, instead instructing users to provide these via environment variables (
TESTRAIL_API_KEY,BROWSERSTACK_ACCESS_KEY), which aligns with security best practices for AI agent tools and developer utilities.
Audit Metadata