dogfood

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or unauthorized command execution, were detected across the skill files or templates.
  • [SAFE]: The skill follows security best practices by specifying the direct use of local browser tools and advising against remote execution runners like npx.
  • [SAFE]: Protective guardrails are implemented to limit the agent's activity to the testing scope and prevent unnecessary access to application source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 04:34 AM