add-ui
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user descriptions to generate UI code, creating a potential surface for indirect prompt injection. \n
- Ingestion points: User input provided through the
[request]hint inSKILL.md. \n - Boundary markers: The instructions do not include specific delimiters or warnings to ignore instructions embedded in the user-provided context. \n
- Capability inventory: The skill is designed to create and update React components, routes, and styles, which involves writing files to the project directory (referenced in
SKILL.mdandassets/apply-cleanup-checklist.md). \n - Sanitization: There are no explicit instructions for the agent to sanitize or validate the generated code for malicious patterns. \n- [EXTERNAL_DOWNLOADS]: The skill references several external resources for framework documentation and component libraries. \n
- Evidence: Links to
tailwindcss.com,ui.shadcn.com,tanstack.com, andreui.ioare included inassets/component-library-integration-checklist.mdandreference/component-library-integration.md. \n - Context: These links point to the official documentation of well-known and established technology services, which is standard for development tools.
Audit Metadata