mockup-device-3d

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly requires embedding user-provided HTML/data "原样嵌入" and to "必须用用户真实数据填充屏幕内容", which would cause any secrets the user supplies (API keys, tokens, passwords) to be reproduced verbatim in the generated output.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). 该技能运行时会把“用户提供的 HTML/文本（外部用户输入）原样/真实数据渲染到屏幕 div 内并进行布局适配”，因此会摄取并处理由外部作者提交的任意自由文本/HTML。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The HTML includes a runtime script tag that loads and executes remote JavaScript from https://cdn.tailwindcss.com, which the skill requires for Tailwind-based rendering, so this external resource executes code at runtime and is a required dependency.