visual-testing-advanced
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on legitimate UI testing practices such as screenshot capture, masking dynamic content, and responsive design validation.
- [REMOTE_CODE_EXECUTION]: The skill references well-known testing frameworks (@playwright/test and @percy/playwright) for its core functionality.
- [DATA_EXFILTRATION]: No evidence of unauthorized data access or exfiltration of sensitive files was found.
- [PROMPT_INJECTION]: No instructions found that attempt to bypass safety guidelines or override agent behavior.
- [PROMPT_INJECTION]: Detected ingestion surface for external web content. 1. Ingestion points: Web page navigation and screenshot capture via Playwright (SKILL.md). 2. Boundary markers: None present. 3. Capability inventory: Web navigation (page.goto), screenshot capture (toHaveScreenshot, percySnapshot). 4. Sanitization: No content sanitization mentioned.
Audit Metadata