ui-ux-gtm
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, focusing on established UI/UX methodologies such as Nielsen Norman Group heuristics and WCAG accessibility standards. It does not perform network operations or access sensitive system resources.
- [COMMAND_EXECUTION]: The skill includes a local Python script
scripts/check-output.py. This script is used as a quality control tool to verify the structure of markdown deliverables generated by the agent. It performs a simple string search for required headers and does not execute the contents of the files it reads. - [EXTERNAL_DOWNLOADS]: The documentation references well-known and trusted accessibility testing tools (e.g., axe DevTools, Lighthouse, WebAIM) and established design resources (Apple HIG, Google Places API). These are standard industry references and do not involve untrusted code execution.
- [INDIRECT_PROMPT_INJECTION]: As a design audit skill, it is intended to process user-provided content (landing page copy, form structures). While this represents an ingestion surface for untrusted data, the skill lacks dangerous capabilities (like network exfiltration or shell execution) that could be exploited via indirect injection, and the impact is limited to the design recommendations provided.
Audit Metadata