Playwright Visual Regression Suite
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The SKILL.md file contains only metadata, descriptive text, and installation commands. It does not contain any executable scripts, tool definitions, or prompt instructions that the agent would follow directly.\n- [INDIRECT_PROMPT_INJECTION]: The skill describes a browser automation tool that interacts with external web content, which presents a potential surface for indirect prompt injection.\n
- Ingestion points: Web pages accessed for screenshot comparison.\n
- Boundary markers: None identified in the high-level description.\n
- Capability inventory: Browser navigation, screenshot capture, and script execution via
page.evaluate.\n - Sanitization: Not specified in the provided documentation.\n- [SAFE]: The identified functionality is consistent with the primary purpose of a visual testing suite. All external references point to the vendor's own infrastructure (agentskillexchange.com).
Audit Metadata