test-generation
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of assisting in Playwright test generation.
- [COMMAND_EXECUTION]: The skill references the use of
browser_run_codewithin a "Site Discovery" workflow. This is a legitimate application of the agent's browser automation tools to identify correct selectors and UI behavior for test scripting. - [CREDENTIALS_UNSAFE]: The provided code examples demonstrate secure development practices by retrieving sensitive information such as usernames and passwords from environment variables (e.g.,
process.env.TEST_USER_EMAIL) instead of hardcoding them into the test files.
Audit Metadata