Security audit
Security checks for vulnerabilities and agentic risk
This is a low-risk writing-style skill with broad activation wording, but it does not request sensitive access, run code, persist data, or perform hidden actions.
Install this only if you want a Chinese prose style assistant. Be aware that broad triggers may make it apply the style to general popular-science or humorous writing requests unless you ask the agent not to use it.
The trigger list includes broad phrases like '科普写作', '趣味写作', and generic style cues that can match many ordinary writing requests unrelated to Wang Xiaobo-style transformation. This can cause unintended skill activation, leading the agent to override user intent or apply stylistic constraints in contexts where they were not requested.
The activation rules rely partly on broad intent-based criteria such as wanting accessible prose or popular science writing, which are common across many unrelated tasks. Ambiguous activation boundaries increase the risk that the skill will engage when the user did not ask for this specific style, causing prompt routing errors or inappropriate stylistic steering.
The scope states that the skill works for "any Chinese-language writing task," and the document consistently frames usage as Chinese writing without offering a language choice. This is a natural-language locale constraint that can force a specific language without explicit user opt-in.
No suspicious patterns detected.
