playwright-test

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the Playwright testing framework and Chromium browser binaries from official repositories and Microsoft's distribution services as part of the standard environment setup.
  • [COMMAND_EXECUTION]: Uses the Bash tool to perform project maintenance tasks, including package installation via npm install and executing the test runner through npx playwright test.
  • [REMOTE_CODE_EXECUTION]: Generates local JavaScript test specifications based on user-provided feature descriptions and project files, which are subsequently executed by the Playwright test runner.
  • [PROMPT_INJECTION]: The skill processes external project files like Form.xml and design.md to influence the generation of test logic, presenting a surface for indirect prompt injection.
  • Ingestion points: Form.xml, design.md, and the project's CLAUDE.md configuration file.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands in these files.
  • Capability inventory: The skill has access to Bash, Read, Write, and Edit tools.
  • Sanitization: No specific sanitization or validation steps are outlined for the content extracted from XML or Markdown files before interpolation into the test script.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 06:14 PM
Security Audit — agent-trust-hub — playwright-test