Security audit
Security checks for vulnerabilities and agentic risk
This is a frontend design guidance skill with no executable code, persistence, credential access, or hidden data handling.
This skill appears safe to install for frontend design assistance. Expect it to influence style choices toward CSS design tokens, OKLch colors, accessibility, responsiveness, and dark mode; consider narrowing its activation wording if you want fewer accidental triggers on general frontend tasks.
The description embeds Chinese trigger phrases without stating that language should follow the user's preference, which can bias activation or responses toward a specific locale. This is primarily a quality and policy-compliance issue that may lead to unwanted language switching or reduced usability for users in other locales.
The activation guidance is broad enough that the skill may trigger for many general frontend or visual requests, causing unnecessary routing to this specialized skill. Overbroad activation can degrade agent behavior, override better-matched skills, and create prompt-scope confusion, though it does not directly introduce code execution or data exfiltration risk.
No suspicious patterns detected.
