Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language writing aid for short-drama emotion pacing, with no executable code, hidden behavior, data access, persistence, or privilege requests.
Install this if you want Chinese-language guidance for short-drama emotional pacing. Be aware that its broad emotion-related triggers may appear in ordinary creative requests, so it may be helpful to invoke it only when working on short dramas, short videos, or emotional arc design.
The trigger list includes several broad, common terms such as '共情', '情感', and '代入感'-style concepts that can appear in many ordinary creative or conversational requests. This can cause the skill to activate outside its intended short-drama design context, leading to prompt hijacking of unrelated tasks, degraded routing quality, or accidental insertion of domain-specific instructions.
The skill metadata and content are written entirely in Chinese and do not indicate language negotiation or fallback behavior, which can cause forced Chinese responses when the user's preferred language differs. While not a direct security exploit, this can undermine system predictability, cause instruction mismatch, and increase the chance of unsafe or incorrect handling in multilingual environments.
This markdown file presents all instructional content in Chinese and does not indicate that users may select another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.
