Security audit
Security checks for vulnerabilities and agentic risk
This is a local Chinese-language 30/60/90 planning helper with some unused audit code in its script, but no evidence of network access, persistence, or hidden system changes.
Install only if you want a Chinese-language local helper for structuring 30/60/90-day plans. Treat the included Python script as a local file processor: give it only planning inputs you are comfortable summarizing, and be aware that the script contains inactive audit modes that should be removed or documented if this package is maintained further.
声明描述的是一个规划类技能，核心应是把目标拆成 30/60/90 天执行方案、阶段成果、资源需求和停止条件。但代码的实际功能是一个通用本地报告/审计脚本，行为完全由 resources/spec.json 的 mode 决定，可用于目录审计、CSV 审计、模式扫描、Skill 合规检查，甚至只是对输入文本做通用结构化整理。虽然在某些 spec 配置下，structured_brief 模式可能生成分章节文本，但代码本身没有任何专门面向“30/60/90 天路线图”的逻辑，也没有内建阶段规划、资源分配或放弃条件分析能力。相反，它具备多项与声明无关的扫描和审计能力。因此其主要用途与声明存在实质性偏差，应判定为不匹配。
The regex-based pattern scanner can inspect arbitrary files and directories for secrets, private URLs, and risky shell commands even though the skill is described as a planning assistant. In this context, hidden scanning functionality is dangerous because it expands data-processing scope to sensitive source content and may surface confidential snippets in generated output.
The script supports multiple analysis modes including directory, CSV, pattern, and skill-audit workflows that are materially broader than the declared purpose of splitting goals into 30/60/90-day execution plans. This scope mismatch can expose local repository contents, summarize arbitrary files, and repurpose the skill as a general auditing tool, increasing data access and misuse risk beyond user expectations.
The trigger example “给我一个可执行路线图” is generic natural language that could overlap with many ordinary planning requests outside this skill’s intended 30/60/90-day decomposition use case. The README does not provide exclusion conditions or tighter scope to distinguish when this skill should activate versus other planning or roadmap skills.
The skill advertises executable behavior via python3 and references local resources, but it does not declare any explicit tool scope such as allowed tools or permissions. This creates an authorization ambiguity where the runtime may permit file access or shell execution beyond what reviewers and users expect, increasing the chance of unintended command execution or filesystem interaction.
The manifest description and primary skill instructions are written in Chinese and present the skill behavior in that language without stating that users may choose another language. This can violate a language/locale policy when a skill effectively forces one language by default rather than offering an explicit choice.
The title, category label, summary, input hint, sections, examples, and risk text are all written in Chinese, which indicates the skill is designed to operate in a specific language. The file does not offer any opt-in, alternative locale, or justification that this is a region-specific skill, so this may violate language/locale policy requirements.
The entire template, including the title and all section headings, is written only in Chinese, which implies the skill output is constrained to a specific language. Under the policy, language-specific behavior should either be optional for the user or clearly documented as a justified locale constraint.
This code generates user-facing report headings and guidance entirely in Chinese, such as '结果', '摘要', and '下一步'. The file provides no user opt-in, locale selection, or documented region-specific justification, which is a natural-language locale policy violation under the stated rules.
The directory and CSV audit functions enumerate files, inspect markdown headings, and summarize tabular data from arbitrary local inputs, which exceeds the declared planning-only scope. In a skill expected to transform user goals into plans, this behavior increases the chance of unintended data disclosure and over-collection from local working directories.
Directory, CSV, pattern, and skill audit reports all emit Chinese-only headings and guidance strings. Because the script enforces a single language across outputs and does not offer language selection, it violates the language/locale policy criteria.
The skill_audit and frontmatter parsing logic perform repository compliance checks unrelated to roadmap planning, allowing the tool to inventory files and inspect skill metadata. While not directly executing code, this broadens the skill into a repository auditor and can reveal project structure and metadata without that behavior being clearly disclosed by the skill description.
This markdown file uses Chinese throughout for headings, descriptions, and audit conclusions, which can amount to a language-policy issue if users are not given an explicit language or locale choice. The file does not indicate that the skill is region-specific or that Chinese is an opt-in requirement.
The entire example output is written in Chinese, and there is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language context. This can violate language/locale policy requirements when a skill imposes a specific language by default without opt-in.
This markdown file presents all testing instructions and expectations only in Chinese, and there is no visible note offering an alternative language or documenting that the skill is intentionally limited to Chinese-speaking users. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue.
No suspicious patterns detected.
