add-ui

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill handles untrusted user input (UI artifact or redesign requests) that are interpolated into prompts to generate React and Tailwind code. This creates a surface for indirect prompt injection.
  • Ingestion points: The skill's primary entry point, the /add-ui command, accepts a user-supplied description in SKILL.md.
  • Capability inventory: The agent has the capability to create and update component and route files across the project directory.
  • Sanitization: The skill mitigates this risk through a mandatory 'preview and apply' protocol, ensuring generated code is inspected by the user before final integration.
  • [COMMAND_EXECUTION]: The instructions guide the agent to perform command-line operations using the shadcn CLI tool (e.g., npx shadcn create, npx shadcn apply). These are standard operations for managing UI component libraries in modern React projects.
  • [EXTERNAL_DOWNLOADS]: The skill references numerous official documentation sites and community registries for UI libraries (such as shadcn/ui, TanStack, and Magic UI) to guide implementation. These references target well-known technology services and official project repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 04:05 PM
Security Audit — agent-trust-hub — add-ui