skills/toolshell/skills/chat-ui/Gen Agent Trust Hub

chat-ui

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONNO_CODE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation instructs users to install components from an external registry at https://ui.inference.sh/r/chat.json using the shadcn CLI tool.
  • [COMMAND_EXECUTION]: Users are prompted to execute npx commands (npx shadcn, npx skills) to add external UI components and related skills to their project.
  • [PROMPT_INJECTION]: The chat UI components create an indirect prompt injection surface as they are designed to process and render untrusted user and assistant messages.
  • Ingestion points: Data enters the context via the content prop of the ChatMessage component and the onSubmit handler of the ChatInput component as seen in SKILL.md.
  • Boundary markers: Usage examples do not include boundary markers or instructions to ignore embedded commands.
  • Capability inventory: No executable code or scripts are included in the skill, resulting in zero local capabilities for potential exploitation.
  • Sanitization: The provided code snippets do not demonstrate sanitization or validation of the message content before display.
  • [NO_CODE]: This skill is entirely comprised of markdown documentation and usage examples, containing no executable assets or script files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:48 PM
Security Audit — agent-trust-hub — chat-ui