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

chat-ui

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references external component registries and images hosted on the vendor's domains (ui.inference.sh and cloud.inference.sh).
  • [COMMAND_EXECUTION]: Instructions are provided for installing components and related tools using 'npx shadcn' and 'npx skills'.
  • [PROMPT_INJECTION]: The skill defines a UI surface for chat messages that represents an indirect prompt injection surface.
  • Ingestion points: Message content in the 'ChatMessage' component in 'SKILL.md'.
  • Boundary markers: None identified in the provided code snippets.
  • Capability inventory: The skill provides static UI components with no direct system access or dangerous capabilities.
  • Sanitization: No explicit sanitization or filtering logic is demonstrated in the implementation examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 12:04 PM