playwright-pro
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external web content and test logs which could contain malicious instructions. It mitigates this by explicitly instructing the agent to treat all such content as data only and never as instructions.
- [COMMAND_EXECUTION]: The skill generates and executes local test scripts as part of its core functionality. It implements a review process (/pw:review) and uses 55 pre-defined templates to maintain code quality and safety while minimizing risks associated with dynamic code generation.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the official Playwright installation command 'npm init playwright@latest' and standard 'npx' commands for execution, which are well-known and trusted developer tools.
Audit Metadata