chat-ui

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to fetch UI components from the official registry at ui.inference.sh using the shadcn CLI tool. It also suggests installing supplementary agent tools from inference-sh and belt-sh via the skills CLI.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The ChatMessage component takes a content prop, and the ChatInput component takes user text via onSubmit (located in SKILL.md).
  • Boundary markers: None explicitly defined in the UI code snippets provided.
  • Capability inventory: The components are primarily for rendering and handling user interaction within a web application environment.
  • Sanitization: The provided documentation focuses on layout and integration; developers must ensure standard React/Markdown sanitization practices are applied when rendering message content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:53 PM
Security Audit — agent-trust-hub — chat-ui