Security audit
Security checks for vulnerabilities and agentic risk
This skill appears to be a disclosed Xiaohongshu public-data research tool that uses a third-party API and local result logs, with no hidden or destructive behavior found.
Install this only if you are comfortable sending Xiaohongshu keywords, URLs, and related query parameters to guaikei.com using your GUAIKEI_API_TOKEN, and with returned public-data results being saved locally in temp logs. Use it for public Xiaohongshu research and internal analysis, not for private content, account actions, or unlawful profiling.
声明描述的是一个面向小红书数据研究的技能，核心应包括对小红书内容、博主、详情页和评论的数据访问与分析。给出的代码却只是 src/utils/args.js，一个通用 CLI 参数解析与帮助文本生成模块。它处理命令行参数、校验、默认值、重复参数冲突、位置参数、错误提示和 help 文本，不包含任何网络请求、页面抓取、API 调用、数据解析、评论分析或与小红书相关的逻辑。按评估标准，这不是单纯的支撑性实现细节，因为当前代码块本身的功能与声明的核心能力完全不一致，表现出明显的描述-行为不匹配。
The declared description presents a full-featured Xiaohongshu data collection and analysis skill. However, the supplied code chunk is a small utility that reads a local metadata file (package.json) and returns the package name. There is no code for network access, Xiaohongshu platform interaction, scraping, searching, filtering, analytics, comment analysis, or trigger handling. This is not merely a supporting implementation detail tied clearly to the declared capabilities; the actual behavior shown is unrelated to the stated primary purpose, so this chunk does not accurately represent the described functionality.
Referenced artifact was not completely inspected
- "这条小红书笔记评论区在吐槽什么 → node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 200"
Referenced artifact was not completely inspected
- "这条小红书笔记评论区在吐槽什么 → node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 200"
Referenced artifact was not completely inspected
- "这条小红书笔记评论区在吐槽什么 → node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 200"
Referenced artifact was not completely inspected
- "这条小红书笔记评论区在吐槽什么 → node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 200"
Referenced artifact was not completely inspected
- "这条小红书笔记评论区在吐槽什么 → node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 200"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 30 条作品发什么 → node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 30"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 30 条作品发什么 → node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 30"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 30 条作品发什么 → node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 30"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 30 条作品发什么 → node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 30"
Referenced artifact was not completely inspected
- "分析这篇小红书爆款笔记为什么火 → node src/xiaohongshu/detail-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy'"
Referenced artifact was not completely inspected
- "分析这篇小红书爆款笔记为什么火 → node src/xiaohongshu/detail-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy'"
Referenced artifact was not completely inspected
- "分析这篇小红书爆款笔记为什么火 → node src/xiaohongshu/detail-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy'"
Referenced artifact was not completely inspected
- "分析这篇小红书爆款笔记为什么火 → node src/xiaohongshu/detail-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy'"
Referenced artifact was not completely inspected
- "分析这篇小红书爆款笔记为什么火 → node src/xiaohongshu/detail-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy'"
The skill requires access to an environment secret (GUAIKEI_API_TOKEN) but does not declare an explicit tool scope or permission boundary. That makes the secret exposure surface less auditable and increases the chance the runtime can invoke capabilities beyond what a user expects, especially in agent environments that rely on manifest-declared permissions for trust decisions.
The skill sends user-supplied Xiaohongshu URLs, keywords, and related query parameters to a third-party service (guaikei.com) but does not present that data flow as a prominent user warning before use. This can lead to unintentional disclosure of sensitive research targets, tracking parameters, or internal investigation subjects to an external processor, which is especially relevant in competitive-intelligence and monitoring workflows.
The manifest description contains broad activation cues such as users asking about Xiaohongshu/XHS/Rednote plus generic needs like data lookup, market research, topic selection, competitor monitoring, KOL screening, or sentiment analysis. In an agent-routing system, this can cause the skill to be invoked for a wide range of common requests, increasing the chance of over-collection, unintended scraping, or execution in contexts the user did not specifically authorize.
Line L127 instructs users to '直接说人话' and provides only a Chinese example utterance for interacting with the skill, while the entire skill README is written exclusively in Chinese. This creates a de facto language requirement without documenting any user language choice or making clear that other languages are supported.
Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.
| --------------- | ------------------------ | --------------------------------------------------------------------------------- |
| `--url`, `-u` | 小红书博主主页链接，必填 | 建议使用主页链接或可解析的短链 |
| `--limit`, `-l` | 返回作品数量上限 | 建议显式传入 `0-10000`；若为0，则获取该博主的互动数据（粉丝量、点赞量、收藏量等） |
| `--help`, `-h` | 显示帮助信息 | 无 |
### 4.4 链接建议
The documentation explicitly supports collecting third-party comment content and creator interaction metrics at scale, but it provides no warning about privacy sensitivity, lawful basis, platform terms, or limits on downstream use. In a research/monitoring skill, this omission can normalize bulk profiling or sentiment analysis of identifiable users and increase the risk of misuse, policy violations, or unsafe handling of personal data.
This JavaScript file contains comments, error messages, and help text entirely in Chinese, including user-visible CLI output such as parameter errors and usage help. Because the skill does not offer user opt-in for language selection or document that it is intentionally limited to a Chinese-speaking context, it violates the language/locale policy criteria.
The help text explicitly requires configuring GUAIKEI_API_TOKEN, and the code later reads process.env.GUAIKEI_API_TOKEN to perform the operation. For a skill described as usable without logging into an account, requiring a provider token is an additional credentialed capability not justified by the stated user-facing purpose.
The script silently persists comment results to disk after reporting success, without an explicit warning or confirmation that user content is being stored locally. This creates a transparency and data-handling risk because operators may believe the tool is only performing transient read-only research while it is actually generating local data artifacts.
Detected: suspicious.exposed_secret_literal