design-system-prep
Warn
Audited by Snyk on Aug 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL의 2단계 자산 분석에서 사용자가 제공한 “웹사이트 URL”을 WebFetch로 라이브 페이지를 분석해 텍스트/이미지/색상 등 자유형 콘텐츠를 LLM이 읽게 되는 경로가 있어, 외부 사용자가 포이즌 텍스트를 웹페이지에 게시하면 에이전트가 그 내용을 간접적으로 섭취할 수 있습니다.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.80). The skill explicitly delegates runtime data/control to internal resources—
moai-designer:design-system-libraryis used as the primary source to populate DESIGN.md (directly controlling generated content) andmoai-designer:design-tokens-transformer/moai-designer:design-sync-uploadare invoked at runtime to perform transformations and uploads (execute external logic), so these external references are runtime dependencies that control outputs or execute code.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata