playwright-expert

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (SAFE): The skill utilizes official NPM commands (npm init playwright@latest, npx playwright install) to download the framework and browser binaries. These are trusted sources from the Microsoft ecosystem.
  • COMMAND_EXECUTION (SAFE): Uses standard CLI commands (npx playwright test, ls, find) for environment detection and test execution. All commands are standard for software development workflows.
  • PROMPT_INJECTION (SAFE): The skill exposes a surface for Indirect Prompt Injection (Category 8) due to browser automation capabilities. Evidence: 1. Ingestion points: page.goto(), page.request.get(). 2. Boundary markers: Absent. 3. Capability inventory: npx playwright test (subprocess execution). 4. Sanitization: Absent. This is a low-risk inherent behavior of browser automation tools and is classified as safe given the primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:52 PM