playwright
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides high-quality, legitimate documentation for Playwright. All code snippets utilize standard library features, and command-line instructions (e.g.,
npx playwright test) are standard for the framework. External references point to the officialplaywright.devdocumentation. - [INDIRECT_PROMPT_INJECTION]: As a tool for web automation, Playwright facilitates the ingestion of data from external websites, creating a surface for indirect prompt injection if an agent processes untrusted DOM content.
- Ingestion points: Navigation to external URLs via
page.goto()inSKILL.md. - Boundary markers: None present in the provided documentation snippets.
- Capability inventory: Shell command execution (
npx playwright) and file system writes for test traces (trace.zip). - Sanitization: The documentation focuses on testing logic and does not implement sanitization for data extracted from external pages.
Audit Metadata