skills/uxkin/agent/ui-states/Gen Agent Trust Hub

ui-states

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an optional MCP server at https://uxkin.com/mcp and provides links to documentation and UI examples on the author's official website (uxkin.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface when processing external UI references via the find_ui_references and get_journey tools. It mitigates this risk by providing explicit instructions to the agent to treat retrieved content as data only, never to follow instructions found within that data, and to avoid reproducing secrets or private information.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 08:35 AM