Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently generates local Chinese educational HTML card decks, but users should only use trusted or sanitized source content because card text is rendered as HTML.
Install only if you want a Chinese Mo-style educational card generator. Treat generated HTML like executable web content: avoid feeding untrusted pasted HTML or hostile articles unless the card text and image URLs are sanitized, and review the output before sharing it.
The template concatenates untrusted card fields such as title, paragraphs, list items, quotes, captions, and image URLs directly into HTML and then assigns the result to innerHTML. If any of those values are user-controlled, an attacker can inject arbitrary markup or script into the generated standalone HTML file, leading to stored XSS when the file is opened or shared.
The skill metadata advertises broad trigger phrases such as “做卡片” and other generic card-related terms, which can cause the agent to invoke this skill in contexts unrelated to HTML knowledge-card generation. Over-broad activation increases the chance of unintended file generation, tool use, or content transformation when the user meant something else, creating a prompt-routing and least-surprise security risk.
The document declares lang="zh-CN" and the visible title/UI copy throughout the template is fixed in Chinese. This creates a locale-specific experience without any visible opt-in, fallback, or indication that the skill is intentionally limited to a Chinese-speaking context.
The HTML root element sets lang="zh-CN", and the visible UI text throughout the page is also fixed in Chinese. For a general-purpose skill asset, this indicates a language/locale constraint without any user opt-in or explanation that the skill is region-specific.
Detected: suspicious.dynamic_code_execution
