recording-browser-flow-as-test

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions for the user to execute npx playwright test to verify generated test files. This is a standard part of the development workflow for the stated purpose.
  • [CREDENTIALS_UNSAFE]: Includes explicit safety guidance under the 'Auth' section, advising users to use environment variables or Playwright's storageState instead of committing secrets to the repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from websites via the browser_snapshot tool to generate locators. While external content is being ingested into the agent's context, this is necessary for the skill's primary function of test generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 05:35 AM