Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local Chinese-language report helper for ranking Skill ideas, with some broader but non-destructive audit code that is not active under its packaged configuration.
Install this if you want a Chinese-language local helper that turns Skill idea inputs into a structured prioritization brief. Treat its output as a draft, not a true quantitative ranking engine, and avoid feeding it unredacted sensitive materials because it processes local files you point it at.
声明描述的是一个面向 Skill 选题优先级排序的工具，核心能力应是依据高频、低门槛、传播性、ROI、风险等维度对候选题目进行排序。实际代码中并没有实现任何明确的评分、排序、优先级计算、市场适配打分或风险/ROI 维度建模。相反，代码是一个通用本地报告生成/审计脚本：它读取 spec.json 决定模式，并可对文本、目录、CSV 文件、代码/文本模式、Skill 目录结构进行扫描与分析，输出结构化报告。这属于明显不同的主用途，并且包含若干未声明的能力（文件系统遍历、内容扫描、模式匹配、合规检查）。虽然输出是报告而非修改系统，但其主要行为与“选题排序”不一致，因此应判定为描述与行为不匹配。
The manifest says this skill ranks Skill topics by frequency, ease, virality, ROI, and risk for market-fit prioritization. However, the code loads a generic spec-driven mode and performs unrelated operations such as directory audits, CSV field summaries, regex pattern scanning, and Skill package structure checks, with no ranking logic for those market-fit dimensions.
The trigger section lists phrases like “帮我给这批 skill 排序” and especially “综合高频和传播性” without defining activation boundaries, exclusions, or narrower invocation context. These examples are generic enough to appear in normal discussion, which could cause unintended skill routing or invocation.
The skill advertises executable capability via python3 and references local resources that imply file read/write behavior, but it does not declare an explicit tool/permission scope. This creates an authorization ambiguity: a caller or platform reviewer cannot reliably tell what filesystem or shell access the skill expects, which increases the chance of over-broad execution in permissive environments.
The file is entirely written in Chinese and includes output requirements such as '使用清晰标题', but it does not indicate that language choice is optional or user-selectable. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless clearly justified as region-specific.
This markdown example output uses Chinese headings and content throughout, which implies the skill may force a specific language for its responses. The file does not indicate any user opt-in, language selection, or justification for a Chinese-only locale, so it may violate language/locale policy requirements.
The generated report strings are hard-coded in Chinese, including section headings and workflow guidance, with no option for the user to select language or locale. This creates a natural-language locale policy concern because the skill enforces a specific language by default rather than offering choice or documenting a justified region-specific constraint.
The pattern scanning logic searches for risky shell commands, secrets, and private URLs, and the skill_audit logic checks repository file completeness and frontmatter validity. Those capabilities may be useful in other tools, but they are not justified by a skill whose declared purpose is ranking content ideas by market-fit criteria.
This markdown file presents the skill's test instructions entirely in Chinese, including the title and all procedural steps. Under the policy for natural-language violations, forcing a specific language without user opt-in is a reportable issue unless the locale constraint is clearly documented and justified, which is not present here.
This markdown file presents all user-facing content exclusively in Chinese, including the title, audit results, and conclusions. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The entire template, including the title and section instructions, is written only in Chinese and provides no indication that users may choose another language. Per the policy category, a skill that implicitly forces a specific language without opt-in can be a natural-language policy violation unless the locale restriction is clearly justified.
No suspicious patterns detected.
