chat-ui
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches chat component registry and configuration from ui.inference.sh, which is the official host for these resources.
- [COMMAND_EXECUTION]: Utilizes npx shadcn and npx skills commands to install and configure the UI components and related development modules.
- [PROMPT_INJECTION]: The skill facilitates the rendering of message content from users and AI models, creating a potential indirect prompt injection surface.
- Ingestion points: Data flows into the ChatContainer via the ChatMessage components in SKILL.md.
- Boundary markers: No specific delimiters or safety instructions are defined in the UI templates to differentiate between instructions and data.
- Capability inventory: This skill is limited to UI presentation and does not include subprocess execution or sensitive file system access.
- Sanitization: No explicit content sanitization or escaping is implemented in the provided component examples.
Audit Metadata