agent-ui

Pass

Audited by Gen Agent Trust Hub on Nov 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides commands to download configuration files and software packages from ui.inference.sh and npm. It also references the belt-sh/cli skill. These resources are directly related to the stated purpose of the skill and come from infrastructure consistent with the tool's vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill describes a UI component that processes user-defined configurations and prompts, creating a surface for potential instruction injection.
  • Ingestion points: The agentConfig and config properties in the Agent component within SKILL.md.
  • Boundary markers: None identified in the provided code examples.
  • Capability inventory: The component includes capabilities for browser-based tool execution (e.g., scan_ui, fill_field), human-in-the-loop approval workflows, and file/image handling.
  • Sanitization: Not demonstrated in the examples; however, the component is a development building block meant to be integrated into secured applications.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 14, 2026, 05:50 AM