Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Chinese-language debate coaching prompt with no code, persistence, credential access, or hidden execution behavior.
Install only if you want a Chinese debate/rebuttal assistant. Review outputs carefully in sensitive personal conflicts, and avoid using the stronger phrasing to harass, threaten, or escalate disputes.
The skill description and content are written to operate in Chinese without any opt-in or language negotiation. This can override user language preferences, reduce transparency for non-Chinese users reviewing the skill, and increase the chance of misunderstanding or unsafe outputs if the user expects another language.
The skill activates on a very broad condition: whenever a user wants to rebut someone, analyze arguments, or organize language. This can cause over-triggering in adjacent contexts such as interpersonal conflict, harassment, or emotionally escalated exchanges, leading the agent to produce adversarial coaching when the user did not explicitly request this specialized behavior.
