Security audit
Security checks for vulnerabilities and agentic risk
This is a frontend design guidance skill with no executable code, persistence, credential use, or hidden data access.
Install this if you want opinionated frontend design defaults and review commands. Expect it to push specific style preferences, such as avoiding Inter/system-ui and applying its design rules during UI work; skip or disable it for projects where those design choices conflict with an existing design system.
The manifest description is written entirely in Chinese and presents the skill behavior as Chinese-first without indicating that users may choose another language. Under the policy, forcing a specific language or locale without opt-in can be a natural-language policy violation.
The listed natural-language triggers include broad phrases like '优化界面' and '让设计更好看', which overlap with common user requests and can activate the skill unintentionally. This creates prompt-scope confusion: the assistant may apply hidden stylistic rules or rewrite code beyond what the user requested, reducing predictability and control.
The execution rule says the skill should activate for broadly defined 'design-related requests', which can cause unintended invocation in many ordinary frontend/UI conversations. Over-broad activation can override user intent, inject unsolicited constraints, and increase the chance that the model follows skill instructions when the user did not explicitly ask for them.
