Security audit
Security checks for vulnerabilities and agentic risk
This skill is a plain Markdown communication-coaching guide with no code execution, persistence, credential use, or hidden data access.
Installers should expect a conversational coaching skill, mostly demonstrated in Chinese, for practicing difficult conversations and roleplay. Ask for another language or a narrower scope if needed, and do not treat it as therapy, legal advice, or crisis support.
The skill description and all example interactions are presented exclusively in Chinese, indicating an implicit language constraint. The file does not state that other languages are supported or give users a choice, which can violate a language/locale policy requiring opt-in or explicit justification.
The usage scenarios and expected outputs are predominantly written in Chinese, and the example response patterns also assume Chinese phrasing, but the skill does not state that it is Chinese-only or offer users a language option. Because the skill description and triggers also include English, this mixed presentation can create an undocumented language constraint.
The trigger phrases are broad, generic requests such as 'how should I say this' and '帮我想想怎么说', which overlap heavily with ordinary assistant use. This can cause the skill to activate outside its intended scope, steering unrelated conversations into roleplay or relationship framing and increasing the chance of inappropriate handling of sensitive situations.
No suspicious patterns detected.
