skills/cabinet-fe/ultra-ui/veltra-ui/Gen Agent Trust Hub

veltra-ui

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill serves as a technical manual for the @veltra UI library, providing component APIs, examples, and TypeScript definitions.
  • [EXTERNAL_DOWNLOADS]: Installation instructions involve standard NPM packages such as @veltra/desktop, @veltra/vite, and unplugin-vue-components from public registries. These are legitimate dependencies required for the library's operation.
  • [PROMPT_INJECTION]: The instructions are purely instructional and technical, with no attempts to override agent behavior, bypass safety filters, or extract system prompts.
  • [DATA_EXFILTRATION]: No evidence of sensitive data access or exfiltration. Examples involving network requests (e.g., in USelect and UAutoComplete) use generic local API paths for demonstration purposes.
  • [COMMAND_EXECUTION]: The skill does not contain any suspicious shell commands, persistence mechanisms, or privilege escalation patterns. Mentions of build commands like bun run skill:gen are standard development workflow instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 02:16 AM
Security Audit — agent-trust-hub — veltra-ui