product-friction
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of Markdown-based guidelines and references. There are no executable scripts (.sh, .js, .py) or configuration files that would permit command execution.
- [SAFE]: All external URLs referenced in the documentation (e.g., Booking.com, IKEA, Stripe, GitHub, Grafana) are used as research examples for UI/UX patterns and point to well-known, legitimate services.
- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected. The skill uses standard instructional language for agent guidance.
- [SAFE]: Metadata fields are consistent with the skill's stated purpose as a product audit tool.
- [SAFE]: While the skill mentions processing external data (support tickets, analytics), it lacks any tools or instructions for data exfiltration or automated execution of untrusted content.
Audit Metadata