chat-ui

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to fetch UI component configurations from https://ui.inference.sh/r/chat.json using the shadcn CLI tool. This is a standard method for integrating remote component registries in modern React development.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines components such as ChatMessage and ChatInput which are designed to ingest and display untrusted data from AI models and users. This creates a potential surface for indirect prompt injection if the rendered content (e.g., Markdown or HTML) is not sanitized by the implementation using these components. The skill documentation suggests using a separate markdown rendering skill which typically handles this sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:18 PM
Security Audit — agent-trust-hub — chat-ui