Security audit
Security checks for vulnerabilities and agentic risk
This is a coherent bilingual writing-editing skill with no code execution, network access, persistence, or hidden data handling.
Install this if you want a Chinese/English prose editor that can flag and rewrite AI-sounding text. In edit mode, review file changes because it may modify prose in place, but the artifacts clearly instruct it to avoid changing protected facts, code, commands, paths, quotes, and metrics.
The comments define separate behavior by language, including different sentence-length units for Chinese vs. English and language-specific connector preferences. Because the file hard-codes locale-dependent writing behavior without any accompanying indication that users can choose or opt into a language setting, it risks enforcing a language/locale policy implicitly.
The document is written as a normative contract and states its goals entirely in Chinese, establishing the skill's expected behavior in a specific language. There is no indication that users may opt into another language or that the Chinese-only constraint is justified by a region-specific use case.
The file explicitly describes preserving "Chinese completeness verbatim," and the entire operational guidance is written only in Chinese. This suggests a language-specific constraint without any opt-in, alternative language path, or justification that the skill is region-specific.
The title and introductory description state the guidance in Chinese and indicate cross-language applicability, but the file does not offer users a language/locale choice or explain why Chinese-only presentation is required. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
No suspicious patterns detected.
