chat-ui
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches component definitions from
https://ui.inference.sh/r/chat.jsonusing theshadcnCLI. - [EXTERNAL_DOWNLOADS]: Recommends adding related functionality from the
inference-sh/skillscollection to be installed via CLI. - [PROMPT_INJECTION]: The skill defines a data ingestion surface (ChatInput, ChatMessage in
SKILL.md) that processes untrusted user input. 1. Ingestion points:ChatInputandChatMessagecomponents inSKILL.md. 2. Boundary markers: None explicitly defined in the provided examples. 3. Capability inventory: No subprocess calls, file-write, or dangerous network operations are present in the skill code. 4. Sanitization: Not implemented at the UI component layer. This surface is inherent to the skill's primary purpose as a chat UI and carries no elevated risk due to the lack of exploitable capabilities.
Audit Metadata