Security audit
Security checks for vulnerabilities and agentic risk
This is a simple educational explanation skill with no code execution, data access, persistence, or hidden privileged behavior.
Installers should expect this skill to steer explanation requests into a detailed, structured teaching format, likely in Chinese unless the agent follows the user's language. Consider narrowing triggers if you want to avoid frequent activation on ordinary explanation requests.
The skill metadata and content are written to produce Chinese-language output by default without explicitly offering user choice of language. This can lead to mismatched responses, reduced usability, and possible misunderstanding when an English or other-language user triggers the skill.
The trigger list contains broad English terms like "teach" and "knowledge" plus generic Chinese phrases such as "讲解" and "解释", which can match many normal user requests unrelated to this specific skill. This can cause unintended activation, routing users into the skill unexpectedly and overriding more appropriate instructions or workflows.
