playwright-skill

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the management of local application lifecycles by executing commands like 'npm run dev' via 'child_process.spawn'. This allows the agent to ensure a target environment is active prior to running tests.
  • [REMOTE_CODE_EXECUTION]: The skill operates by generating JavaScript automation scripts and saving them to the '/tmp' directory for execution. This dynamic code generation is the intended method for performing web interactions.
  • [DATA_EXFILTRATION]: The skill includes functionality to navigate to URLs and inspect page content, but no unauthorized data transfer logic was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:54 AM