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_unsafedescribed 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_evaluateandbrowser_run_code_unsafetools 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