Security audit
Security checks for vulnerabilities and agentic risk
This is a small Chinese WeChat Moments copywriting helper with no evidence of hidden access, persistence, network activity, or destructive behavior.
Install this only if you want Chinese WeChat Moments marketing copy prompts. Review generated posts before publishing, especially because the templates are oriented toward private-domain marketing and audience targeting.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
请直接输出文案，不要解释。`;
return prompt;
}
// 主函数
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
请直接输出文案，不要解释。`;
return prompt;
}
// 主函数
The manifest’s natural-language descriptions consistently define the skill as a Chinese '朋友圈文案生成器' and all example usages/topics are in Chinese, with no indication that users can choose another language. This imposes a specific language/locale behavior without documented user opt-in or a stated region-specific justification.
The prompt template instructs the model entirely in Chinese and directs it to generate a Chinese social-media post. This imposes a specific language on users without any visible opt-in or configurable locale selection, which matches the language/locale policy violation category.
No suspicious patterns detected.