frontend-ui-testing
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with and verify untrusted content from rendered web pages and browser consoles.
- Ingestion points: Browser DOM, page text, and console logs retrieved during testing in the
SKILL.mdfile. - Boundary markers: The instructions do not provide explicit delimiters or instructions to ignore commands embedded in the application being tested.
- Capability inventory: The skill utilizes the Browser capability and may execute Playwright scripts as subprocesses to verify UI states.
- Sanitization: No specific sanitization of external content from the browser or application state is defined.
- [SAFE]: The skill's behavior is consistent with its primary purpose of UI testing. It includes constraints to prevent unauthorized dependency installation and avoids persistent modifications or data exfiltration.
Audit Metadata