playwright

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists of informational documentation and guidelines for using the Playwright testing framework. No malicious patterns or executable scripts are included.
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation on playwright.dev, which is the established domain for this well-known testing tool.
  • [COMMAND_EXECUTION]: Common tasks list standard usage of the Playwright CLI (e.g., pnpm exec playwright test), which is consistent with the skill's primary purpose.
  • [INDIRECT_PROMPT_INJECTION]: As a tool designed for browser automation, there is an inherent surface for indirect prompt injection if the agent processes untrusted web content.
  • Ingestion points: Browser content retrieved via Playwright during test execution or verification.
  • Boundary markers: None explicitly defined in the skill documentation.
  • Capability inventory: Shell execution of Playwright CLI commands (SKILL.md).
  • Sanitization: Not implemented within this instructional skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:52 PM
Security Audit — agent-trust-hub — playwright