education-learning-material
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). SKILL.md의
content인자(외부 사용자가 제공할 수 있는 학습 내용)를 그대로 HTML로 렌더링하며, mermaid/ECharts/KaTeX/highlight.js/AOS 주입은 콘텐츠에 “해당 블록/시그널이 등장할 때” 수행되어 LLM이 해당 텍스트를 사전에 특정 항목으로 찾아 선택하지 않는 형태로 런타임에 자유형 텍스트를 간접 프롬프트 인젝션 표면에 노출할 수 있습니다.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's HTML generation includes runtime imports of third-party JS from CDNs (e.g. https://cdn.jsdelivr.net/npm/mermaid@11/dist/mermaid.esm.min.mjs) which will be fetched and executed in the user's browser, so the skill relies on external scripts that execute remote code at runtime.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata