Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent study-material generator with no bundled executable code, persistence, credential handling, or hidden destructive behavior.
Installers should expect this skill to create learning-material files from provided study content and possibly use search if the user chooses that path. Review generated study content for accuracy, especially when no source material is uploaded.
The trigger list includes broad everyday phrases such as “学习材料”, “笔记生成”, “测验”, and “课件”, which are likely to overlap with ordinary user conversations and can cause unintended skill activation. This increases the chance that the skill takes over contexts the user did not explicitly intend, potentially redirecting workflows, generating files unnecessarily, or altering expected assistant behavior.
整个技能说明与输出要求均以中文固定描述，未见允许用户选择语言或根据用户偏好切换语言/地区设置的说明。按规则，这类强制语言/locale 约束若无用户 opt-in 或明确业务正当性，构成自然语言策略风险。
No suspicious patterns detected.
