skills/inference-sh/skills/widgets-ui/Gen Agent Trust Hub

widgets-ui

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to install components using npx shadcn@latest add https://ui.inference.sh/r/widgets.json. This fetches component definitions from the author's official registry domain.\n- [EXTERNAL_DOWNLOADS]: The skill references the installation of an external CLI tool using npx skills add belt-sh/cli.\n- [INDIRECT_PROMPT_INJECTION]: The WidgetRenderer serves as a surface for indirect prompt injection as it renders UI based on structured data that may be generated from untrusted sources.\n
  • Ingestion points: The widget prop in the WidgetRenderer component (SKILL.md).\n
  • Boundary markers: The documentation does not specify explicit delimiters or 'ignore' instructions for the widget JSON content.\n
  • Capability inventory: The system supports interactive elements including buttons, inputs, and form submissions (onClickAction, asForm).\n
  • Sanitization: The documentation does not explicitly mention sanitization or validation logic for the rendered JSON content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:38 PM
Security Audit — agent-trust-hub — widgets-ui