Security audit
Security checks for vulnerabilities and agentic risk
This is a narrow Xiaohongshu title-writing helper with no hidden access, persistence, network behavior, or destructive capability found.
Install this if you want Chinese Xiaohongshu-style title generation. Be aware that it is intentionally optimized for emotional, click-oriented marketing copy and may activate too broadly if your agent routes generic topics to it.
The instruction requires outputs to be "Native, emotional, and visually structured titles" and the rest of the file centers the skill on Xiaohongshu/RedNote content conventions, effectively imposing a specific locale/language style. There is no user opt-in, alternative language option, or explicit justification that the skill is limited to a Chinese-platform context.
The trigger condition is effectively any user-provided raw text or topic, which is so broad that the skill can activate in many ordinary conversations without clear user intent to use this specialized title-generation behavior. Over-broad activation increases the chance of inappropriate routing, unexpected behavior, and misuse of the skill in contexts where persuasive CTR-optimization content was not requested.
The examples library is entirely written in Chinese and presents the content categories and sample outputs only in that language. There is no indication that Chinese is optional, selectable by the user, or justified as a region-specific constraint, which can violate a language/locale choice policy.
The reference material is entirely oriented around Chinese-language marketing phrases and templates, including explicit Chinese keyword dictionaries and example copy, with no indication that language choice is optional. This can violate language/locale policy when a skill implicitly constrains outputs to a specific language without user opt-in or documented regional justification.
The docstring and rule set are tailored to Xiaohongshu-specific Chinese title norms, including Chinese banned phrases and required emoji/punctuation heuristics. This creates a locale/language-specific constraint without any user opt-in or documented justification in the file, which matches the language/locale policy violation category.
No suspicious patterns detected.
