playwright

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill's instructions or supporting scripts.
  • [EXTERNAL_DOWNLOADS]: The maintainer-facing update action (implemented in scripts/update.sh) fetches package metadata and tarballs from the NPM registry to synchronize the vendored baseline with the upstream @playwright/cli package. This utilizes well-known services for standard maintenance.
  • [COMMAND_EXECUTION]: The skill relies on the playwright-cli tool for browser automation. The execution environment is appropriately scoped via the allowed-tools frontmatter configuration, which limits the agent to the specific CLI tool.
  • [DATA_EXFILTRATION]: While the skill manages sensitive browser data such as cookies and storage state, it does so for legitimate automation purposes and provides explicit documentation on security best practices, including the use of .gitignore to prevent credential exposure.
  • [SAFE]: The PowerShell script scripts/force-chrome-foreground.ps1 is a benign helper that uses standard Win32 APIs to manage window focus during headed browser sessions on Windows.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 07:55 PM
Security Audit — agent-trust-hub — playwright