Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-localized UI/UX design guidance skill with no executable code, credential handling, persistence, or destructive behavior.
Install this if you want Chinese-localized UI/UX guidance. Be aware that its broad triggers may steer ordinary UI, UX, layout, dashboard, landing page, or frontend tasks toward Chinese product conventions unless your agent or platform limits when the skill activates.
The metadata and content fix the skill to zh-CN and Chinese design conventions without indicating user choice, fallback behavior, or consent. In practice this can bias responses toward a locale-specific output even when the user did not request Chinese language or mainland-China-specific UX patterns, reducing reliability and potentially causing inappropriate localization.
The activation conditions are very broad and include generic requests like UI generation, frontend implementation, and review tasks. This can cause the skill to activate on many unrelated or only partially related requests, steering outputs toward this skill’s assumptions and increasing the chance of unwanted prompt influence, mis-scoping, or accidental override of user intent.
The manifest hard-codes the locale as "zh-CN" without any indication of user choice, fallback behavior, or opt-in. While not directly dangerous in isolation, it can cause the skill to operate in an unexpected language context, leading to confusion, misinterpretation, or inappropriate activation for users who did not request Chinese-language output.
The trigger list includes very broad everyday terms such as "设计", "UI", "UX", "界面", and "布局", which are likely to appear in many unrelated conversations. This can cause unintended activation of the skill, increasing the chance that the agent injects design-oriented behavior or content when the user did not explicitly request this skill.
No suspicious patterns detected.
