ui-test-playwright
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The
README.mdprovides installation instructions that includepowershell -ExecutionPolicy Bypass. This flag allows scripts to run by bypassing the default Windows PowerShell execution policy. - [REMOTE_CODE_EXECUTION]: The entry point
scripts/run-tests.shinvokesnpx playwright test. This command fetches and executes the Playwright package from the npm registry, which is a standard method for running this trusted testing tool. - [PROMPT_INJECTION]: The skill handles project-specific data which introduces a surface for indirect prompt injection (Category 8).
- Ingestion points: Project scope, constraints, and environment details are ingested in
prompts/ui-test-playwright.md. - Boundary markers: The instructions lack explicit delimiters to separate user-provided content from agent instructions.
- Capability inventory: The skill facilitates local script execution via
scripts/run-tests.sh. - Sanitization: No input sanitization or validation processes are described for the external project context.
Audit Metadata