widgets-ui
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download a UI registry component using
npx shadcn@latest add https://ui.inference.sh/r/widgets.json. This is a standard practice for theshadcn/uiecosystem to import shared components. - [REMOTE_CODE_EXECUTION]: The documentation references commands like
npx skills add belt-sh/cliandnpx shadcn@latest add .... These are developer-initiated CLI commands used for setup and dependency management within a standard development workflow. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to render UIs based on structured agent responses (JSON). This creates an attack surface where an agent processing untrusted data could potentially be influenced to generate specific UI elements. However, the skill uses a declarative schema which inherently limits the execution scope compared to raw HTML or script injection.
- [SAFE]: All referenced domains (
ui.inference.sh,inference.sh,cloud.inference.sh) and packages (belt-sh/cli) are consistent with the documentation's purpose and the author's infrastructure, representing standard generative UI functionality.
Audit Metadata