playwright-skill

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's instructions and code snippets follow security best practices and do not exhibit malicious behavior.
  • [EXTERNAL_DOWNLOADS]: Fetches official Playwright Docker images from Microsoft and installs standard testing and coverage packages from npm, such as @playwright/test, @axe-core/playwright, and nyc.
  • [COMMAND_EXECUTION]: Provides guidance for using a specialized browser automation CLI tool through safe shell commands.
  • [DYNAMIC_EXECUTION]: Includes patterns for executing JavaScript snippets within a controlled browser environment for tasks like complex scraping and state management.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external website content via browser automation commands (e.g., in playwright-cli/advanced-workflows.md), which represents an inherent surface for indirect prompt injection. 1. Ingestion points: playwright-cli snapshot and run-code reading page content. 2. Boundary markers: Absent. 3. Capability inventory: Bash tool, file operations, network access. 4. Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 06:38 PM