Security audit
Security checks for vulnerabilities and agentic risk
This is a simple Xiaohongshu title-writing skill with no code execution, data access, persistence, or hidden authority.
Before installing, expect this skill to answer in a Xiaohongshu/Chinese marketing-title style. For generic title-writing requests, you may need to specify another format or language if you do not want Xiaohongshu-style output.
The activation triggers include generic phrases like '生成标题' and 'title generator', which can match many unrelated user requests and cause the skill to activate outside its intended Xiaohongshu-specific scope. Over-broad activation increases the chance of unintended routing, irrelevant automation, or interference with more appropriate skills, especially in multi-skill agent environments.
The manifest and content consistently target Chinese-language Xiaohongshu usage, including Chinese tags and examples, but do not explicitly state that the skill is region/language-specific or offer an opt-in choice for output language. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy concern.
No suspicious patterns detected.
