playwright-mcp

Warn

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill defines a tool browser_run_code_unsafe described as 'Execute arbitrary code (use with caution)'. This allows the agent or an attacker to execute arbitrary logic within the browser environment.
  • [DYNAMIC_EXECUTION]: The browser_evaluate and browser_run_code_unsafe tools allow for runtime execution of JavaScript strings. While standard for browser automation, providing a specifically named 'unsafe' execution tool increases the risk of malicious payload injection or accidental security bypasses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 8, 2026, 10:53 AM
Security Audit — agent-trust-hub — playwright-mcp