Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only writing aid for medical-aesthetics educational content, with no code execution, credentials, external calls, or persistence in the inspected artifacts.
Before installing, treat this as a specialized content-writing skill for Chinese medical-aesthetics marketing and educational material. Generated medical or treatment-related claims should still be reviewed by qualified staff for accuracy, local advertising rules, and patient-safety boundaries.
Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.
## Core principle / 核心原则
**Always answer the reader's real question first.**
内容必须先回答问题，再展开解释。
不要让品牌先出现，不要让结论埋得太深。
The README describes the skill almost entirely in Chinese and all example invocations are written in Chinese, which signals a default language expectation for use. There is no statement that users may choose another language or locale, so the skill description effectively imposes a specific language context without opt-in.
The instruction requires the opening answer to appear within '150–250 Chinese characters', which imposes a specific language/locale expectation. Elsewhere the skill is bilingual, but it does not clearly offer the user a choice of output language or explain that Chinese-only constraints are optional.