Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Chinese Xiaohongshu copywriting skill with no code execution, persistence, credential access, or hidden data handling.
Install this only if you want Chinese Xiaohongshu-style marketing copy. Review generated claims before posting, especially health, finance, product-performance, or endorsement language, but the skill itself does not show security-sensitive behavior.
The file requires that all正文 use the first-person pronoun "我", and the entire skill specification is written to produce Chinese-language Xiaohongshu copy. There is no indication that users may opt into another language or locale, which creates a natural-language locale constraint without user choice.
The entire template library is written as fixed Chinese-language copy for titles, hooks, and content structures, with no indication that the skill is optional, locale-specific, or configurable by user preference. This can violate language/locale policy because it implicitly constrains outputs to Chinese without user opt-in or justification.
The markdown explicitly states '中文输出', which imposes a fixed language requirement. Under the policy rule, forcing a specific language without offering the user a choice or documenting a justified locale restriction is a natural-language policy violation.
No suspicious patterns detected.
