build-ui
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill defines a purely instructional workflow for frontend development and user interface review. It does not include any executable scripts, shell commands, or automated system modifications.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential vulnerability surface when the optional UXKIN MCP tools are used to ingest external design references. It includes specific boundary instructions for the agent to treat all tool outputs as data only, explicitly warning the agent to never follow instructions found within that data and to avoid reproducing sensitive content or branding from the samples.
- [EXTERNAL_DOWNLOADS]: The skill references the author's official domain (uxkin.com) and GitHub repository for documentation and optional design tools. These resources are consistent with the vendor identity (UXKIN) and are provided for user-initiated integration only.
Audit Metadata