playwright-mcp-workflows

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for browser automation and testing workflows, focusing on reliability and determinism.
  • [EXTERNAL_DOWNLOADS]: The skill instructions involve installing the playwright library via npm and browser binaries using npx playwright install. These are standard procedures for a well-known, reputable automation framework.
  • [COMMAND_EXECUTION]: The skill includes shell commands for project initialization (npm init -y) and environment setup. These are common developer operations for establishing a local testing environment.
  • [PROMPT_INJECTION]: The skill processes content from target websites, creating a potential surface for indirect prompt injection. The skill mitigates this by recommending best practices such as using stable selectors and explicit UI state validation to ensure the agent remains in control of the automation flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 11:08 PM
Security Audit — agent-trust-hub — playwright-mcp-workflows