skills/xiaomi/hiui/hiui-design/Gen Agent Trust Hub

hiui-design

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides a robust set of instructions and templates for UI generation. All identified patterns are consistent with its stated purpose as a design system utility.
  • [COMMAND_EXECUTION]: The skill instructions (SKILL.md) guide the agent to run a local script (scripts/plan-page-task.mjs) to generate task plans. This is a legitimate use case for a development-oriented AI agent skill and does not involve high-risk arbitrary command execution or privilege escalation.
  • [DATA_EXFILTRATION]: No patterns of data exfiltration were found. The skill does not perform unauthorized network requests or access sensitive local files (e.g., SSH keys, AWS credentials).
  • [PROMPT_INJECTION]: The instructions do not contain malicious overrides, role-play jailbreaks, or attempts to bypass safety filters. It maintains a strictly technical and instructional tone.
  • [EXTERNAL_DOWNLOADS]: Dependencies listed in the package.json files are standard packages from the official NPM registry belonging to the @hi-ui and @hiui-design namespaces, which are consistent with the skill's authorship.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 05:43 AM
Security Audit — agent-trust-hub — hiui-design