Skills
skills/halt-catch-fire/skills/agent-ui/Gen Agent Trust Hub

agent-ui

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to fetch a component registry file from https://ui.inference.sh/r/agent.json using the shadcn CLI to integrate the agent UI.
  • [COMMAND_EXECUTION]: Provides instructions to use npx and npm for installing necessary developer tools, related skills, and the @inferencesh/sdk package.
  • [CREDENTIALS_UNSAFE]: Includes a best-practice recommendation to store the INFERENCE_API_KEY in a .env.local file, which is a standard method for managing secrets in Next.js applications.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:15 AM
Security Audit — agent-trust-hub — agent-ui