tools-ui

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches UI registry and component code from ui.inference.sh using the shadcn CLI tool during the setup phase.
  • [INDIRECT_PROMPT_INJECTION]: The ToolResult component processes and displays results from tool executions, which may contain untrusted data from external sources (e.g., web search results).
  • Ingestion points: The 'result' prop in the ToolResult component within SKILL.md.
  • Boundary markers: None specified in the documentation.
  • Capability inventory: React-based UI rendering.
  • Sanitization: No explicit sanitization or escaping logic is described; the skill relies on default React rendering protections.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:54 PM
Security Audit — agent-trust-hub — tools-ui