Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only frontend interaction design checklist with no hidden execution, data access, persistence, or credential behavior.
This skill appears safe to install as a design-process helper. Users should expect it to make frontend work more structured and prescriptive, especially around mandatory UI states and destructive-action confirmations, but it does not add code execution or privileged access.
This eval prompt is written entirely in Chinese, and the file provides no indication that other languages are supported or that the skill is intentionally restricted to a Chinese-speaking or region-specific context. Under the policy, locale or language constraints should be optional or explicitly justified rather than implicitly enforced.
This eval prompt is written entirely in Chinese, which implies the skill is expected to operate in Chinese for at least this evaluation path. Because the file does not indicate that language selection is optional or user-chosen, it presents a natural-language locale policy concern under the rule for forced language without opt-in.
The prompt on this line is in English while the other example is in Chinese, but the file contains no natural-language guidance about supported languages or how locale is selected. This can create an implicit, undocumented language policy instead of an explicit user choice.
