qa-testing-playwright

Pass

Audited by Gen Agent Trust Hub on Nov 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Playwright framework and browsers using standard package managers (npm and npx). The metadata also includes an installation command that fetches the skill's markdown content from a public GitHub repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as a template for generating tests based on user application data, which is an inherent attack surface for indirect prompt injection.
  • Ingestion points: User requests defining test scenarios and application UI identifiers (e.g., labels, roles) in SKILL.md.
  • Boundary markers: None defined for isolating user-provided application context from instructions.
  • Capability inventory: Subprocess execution (npx playwright test) and file creation capabilities defined in the project structure.
  • Sanitization: No sanitization of user-provided input or application data is implemented in the reference templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 9, 2026, 03:12 PM