dogfood

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a legitimate workflow for QA testing. It leverages standard browser automation tools (browser_navigate, browser_vision, browser_console, etc.) to identify functional, visual, and console errors.
  • [SAFE]: Data handling is restricted to capturing screenshots and generating reports within a user-defined or default local output directory. There is no evidence of unauthorized data exfiltration or credential harvesting.
  • [SAFE]: The skill uses a template system for reporting that encourages structured data collection without executing dynamic or remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:55 AM
Security Audit — agent-trust-hub — dogfood