Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language prompt-template skill with no executable code, persistence, credential handling, or hidden data access.
Install if you want a Chinese prompt-template library. Review generated prompts before reusing them with external AI tools, especially when they include private work data, API credentials, scraping targets, or scheduled automation details.
The activation description is very broad and covers generic prompt-writing and optimization requests, which can cause the skill to trigger in many ordinary conversations. Over-broad activation increases the chance of unintended routing, context capture, and interference with more appropriate skills, especially when user input includes sensitive drafting tasks.
The skill content and examples are written entirely in Chinese and implicitly assume Chinese-language interaction without stating that limitation or offering language selection. This can lead to incorrect prompt generation, user confusion, or mishandling of instructions when invoked for users operating in other languages or locales.
This JSON eval file contains multiple natural-language prompts, descriptions, and expected outputs exclusively in Chinese. Because SQP-3 applies to all file types and flags language-policy constraints without opt-in or justification, this appears to enforce a specific language behavior implicitly.
The template prompts and section content are presented in Chinese, while the file does not state that the skill is Chinese-only or offer users a language/locale choice. This can violate language/locale policy guidance when a specific language is effectively imposed without opt-in or justification.
This markdown file contains user-facing template content entirely in Chinese, while the surrounding headings and usage notes are in English. Because the skill does not offer users a language/locale option or explain that it is intentionally region- or language-specific, it creates a natural-language policy issue under the language-choice rule.
This markdown file uses generic activation descriptions like 'User wants to plan a trip' and the embedded prompts repeatedly use broad phrases such as '帮我制定' and '帮我写'. These are common everyday requests without explicit trigger boundaries, exclusions, or narrow context, which could cause unintended invocation if reused as skill triggers.
This markdown file defines invocation-style templates using generic phrases such as “帮我写一份PPT的内容”, “帮我分析这份Excel数据”, and “帮我整理一份会议纪要.” These are broad everyday requests rather than narrowly scoped activation phrases, and the file does not provide exclusion conditions or negative examples to clarify when the skill should or should not be invoked.
This markdown file contains a natural-language usage reference and begins by describing itself in Chinese, while the rest of the templates are also written in Chinese. Because the skill/reference material effectively forces a specific language without user opt-in or a stated region-specific scope, it conflicts with the language/locale policy criteria.
This markdown file contains user-facing prompt templates exclusively in Chinese for WeChat, Xiaohongshu, and Zhihu, but it does not state that the skill is China-specific or provide an opt-in language/locale choice. That can violate language/locale policy where skills should not force a specific language without user choice or documented justification.
This markdown file includes multiple generic 'Use when' conditions such as 'User wants expert-level analysis' without defining explicit trigger phrases, boundaries, or exclusion conditions. Because SQP-1 applies to markdown files, these broad activation descriptions could cause the skill or template set to be invoked in overly general situations.
Phrases like 'User wants roleplay interaction,' 'User needs comprehensive analysis,' and 'User wants multiple options' are high-level and ambiguous rather than narrowly scoped. The document does not provide specificity on how to distinguish these cases from ordinary requests, which fits the vague-trigger category for markdown files.
This markdown file contains user-facing prompt templates almost entirely in Chinese, which effectively imposes a specific language for interacting with the skill. Under the policy, language constraints should either be optional, user-selectable, or clearly justified.
This markdown file contains natural-language instructions and example prompts exclusively in Chinese from L09 onward, while giving no indication that language selection is optional or intentionally region-specific. That can violate a language/locale policy requiring user choice or explicit justification for a forced locale.
This markdown file mixes English headings with prompt content that is consistently written in Chinese, effectively steering users toward a specific language for skill output. Under the policy, forcing a language or locale without opt-in can be a natural-language policy violation when no alternative or justification is provided.
The natural-language content and template examples are entirely in Chinese, while the file does not state that the skill is region-specific or provide an opt-in language choice. This can violate language/locale policy expectations when users are not given a choice or justification for the enforced language.
The natural-language templates from L009 onward require Chinese-language interaction, but the file does not state that the skill is Chinese-only, offer multilingual support, or ask for user language preference. This can violate language/locale policy where skills should not force a specific language without opt-in or justification.
No suspicious patterns detected.
