anti-ai-design
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional text and design tokens (CSS variables) for the agent to follow during code generation.
- [SAFE]: There are no detected patterns for prompt injection, data exfiltration, or unauthorized command execution.
- [SAFE]: All external references (such as mentions of Lucide or Heroicons) are standard industry design tools and do not involve remote code execution or installation of untrusted packages.
- [SAFE]: The localized description files and the core instructions use legitimate non-English terminology (e.g., '去AI设计感') that is relevant to the skill's purpose and does not represent obfuscation or homoglyph attacks.
Audit Metadata