Security audit
Security checks for vulnerabilities and agentic risk
This is a Markdown-only Chinese literary writing-style skill with no code execution, persistence, credential access, or hidden data movement.
Install this only if you want a strong Chinese Lu Xun-inspired rewrite mode; invoke it explicitly for that style, and avoid relying on it for neutral editing, marketing copy, or user-facing text where a warmer or different-language tone is required.
The trigger list is broad and stylistic, using common phrases like '不要鸡汤', '力量感', and '怀疑' that can match ordinary writing requests far beyond the intended niche. This can cause unintended activation and style takeover, leading the agent to apply a strong ideological or tonal transformation when the user likely wanted general editing help.
This markdown file is entirely written as Chinese-only instructional content and gives no indication that users may choose another language. Under the policy, language or locale constraints should either be optional for the user or clearly justified as region-specific; neither is stated here.
This markdown file is entirely framed as a Chinese-only writing template, beginning with a Chinese title and then prescribing a specific Chinese literary style throughout. Because the skill does not indicate that the language choice is optional or limited to a justified region-specific context, it creates a natural-language locale constraint without user opt-in.
This markdown file is written entirely in Chinese from the title onward, and nowhere offers an alternative language or indicates that Chinese is an intentional, region-specific requirement. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is in scope.
This markdown file is written entirely in Chinese and repeatedly frames the prescribed writing approach as mandatory, without offering any language or locale choice or noting that it is intended for a Chinese-speaking audience. Under the policy scope for natural-language violations, forcing a specific language without user opt-in is in scope.
The entire skill content is written as prescriptive guidance in Chinese and presents itself as a general writing skill, but it does not offer any language or locale opt-in. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the constraint is clearly documented and justified.
This file is written entirely in Chinese and strongly frames the skill around a fixed Chinese-language stylistic mode without indicating any option to adapt to the user's requested language. In an agent setting, forcing output language/locale without opt-in can cause user confusion, unusable responses, and policy bypass of user preference or platform locale expectations, though it is not directly malicious.
The description is entirely framed around Chinese literary style and Chinese trigger phrases, and the tags explicitly mark the skill as 'chinese'. While the specialization may be intentional, the file does not state that this language constraint is optional or user-selected, which can conflict with language-choice policy expectations.
