chat-ui

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to download UI component registry data from https://ui.inference.sh/r/chat.json using the shadcn CLI.
  • [COMMAND_EXECUTION]: Provides instructions to execute shell commands using npx for adding tools (belt-sh/cli) and remote components (shadcn@latest add ...).
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The documented ChatMessage component (via the content prop) and ChatInput component (via onSubmit) ingest external data.
  • Boundary markers: None explicitly defined in the provided code snippets.
  • Capability inventory: The skill environment allows for remote component installation via npx shadcn and additional skill installations via npx skills.
  • Sanitization: Sanitization of message content is not explicitly shown in the provided UI examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — chat-ui