Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language markdown skill for generating aesthetic design-system skills; it is coherent and non-executable, but users should review generated skills before enabling them.
Install this only if you want a Chinese-language aesthetic-system generator. Review any generated Skill files before enabling them, especially because the skill can write new skills under a skills directory and may activate on broad design phrases like visual style or color scheme.
The trigger list is very broad and includes common phrases like '设计风格', '视觉风格', and '配色方案', which can cause the skill to activate in ordinary design conversations where the user did not intend to invoke this specialized skill. Overbroad activation increases the chance of misrouting user requests, context capture beyond intended scope, and accidental execution of downstream generation behavior.
The skill is written entirely in Chinese without a documented language/locale constraint or fallback behavior, which can cause operators or orchestrators to misinterpret its instructions or activate it for users who cannot understand its outputs. This is primarily a safety and reliability issue: misunderstanding of capability, scope, or generated content can lead to incorrect use and weakened human review.
The file is entirely written in Chinese and appears to define the skill’s operating instructions and output behavior without any visible user-locale negotiation or documented justification. This can cause the agent to respond in an unexpected language, reducing transparency and making it harder for users or downstream reviewers to validate outputs, especially in safety-sensitive review chains.
This markdown file applies to the vague-trigger category. Line L314 says the generated description must contain a one-line aesthetic description plus trigger words, but it does not define a bounded list of trigger phrases, activation constraints, or negative examples, which can lead to overly broad invocation behavior when the skill is assembled.
This markdown exemplar uses Chinese throughout the title, input, output, and explanatory sections, which effectively forces a specific language for users reading or reusing the skill. The file does not indicate that Chinese is optional, user-selected, or required for a documented region-specific purpose.
The entire exemplar is written as a prescriptive output template in Chinese, and there is no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-only audience. Under the policy, natural-language files that impose a language or locale without opt-in should be flagged.
This markdown file presents all user-facing descriptions and templates exclusively in Chinese. Under the policy, forcing a specific language without offering a language or locale choice can be a natural-language policy violation unless the locale constraint is clearly documented and justified.
This markdown file presents all skill content in a single language and does not indicate that the user can opt into another language or that the skill is intentionally region-specific. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
该 markdown 文件通篇以中文撰写，且未见任何说明表明这是可选语言、区域特定内容，或为用户提供其他语言选择。根据规则，若技能在自然语言层面强制特定语言而未获得用户 opt-in，可构成语言/locale 政策问题。
