Playwright E2E Testing
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill body consists of documentation and TypeScript code examples for creating robust web tests using Playwright. All patterns, such as the Page Object Model and authenticated state reuse, represent established best practices in the testing community.
- [EXTERNAL_DOWNLOADS]: The metadata includes an installation command that fetches the SKILL.md file from a GitHub repository (omarrohit20/ui_automation) using curl. This is a standard procedure for installing agent skills and targets non-executable documentation content.
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for generating code based on user testing requirements, creating a surface for indirect prompt injection. However, the risk is inherent to the skill's primary function as a coding assistant. Evidence Chain: 1. Ingestion points: User requests for test creation or debugging (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: File writing and script execution via agent-provided tools. 4. Sanitization: The skill does not provide specific instructions for sanitizing user-provided input before inclusion in generated code.
Audit Metadata