agent-ui
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a UI component registry from ui.inference.sh and installs the @inferencesh/sdk package. These are official vendor resources required for the skill's functionality.
- [REMOTE_CODE_EXECUTION]: Instructions include using npx to add components from the vendor's registry. This is a standard installation method for shadcn-style UI components and is considered safe when originating from trusted service domains.
- [SAFE]: No malicious patterns, such as prompt injection or data exfiltration, were detected. The environment variables and proxy setup follow standard security practices for AI integrations.
Audit Metadata