Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Xiaohongshu public-data integration that calls the GUAIKEI API with a user-provided token and saves returned JSON locally.
Before installing, make sure you trust GUAIKEI with the Xiaohongshu keywords or links you query and with the GUAIKEI_API_TOKEN used for billing/access. Expect fetched public data to be saved as local JSON logs in the system temp directory for later analysis.
声明描述的是一个面向小红书社媒分析的完整数据获取与分析技能，核心能力应包括平台内容抓取、评论获取、互动数据读取，以及后续的聚类和情感分析。但提供的代码仅是 src/utils/args.js，一个与业务无关的通用 CLI 参数解析模块：负责读取命令行参数、处理别名、默认值、布尔参数、位置参数、重复参数检测、错误提示和帮助文本生成。该代码没有网络请求、没有访问小红书资源、没有任何数据抓取或分析逻辑，也没有与声明四大能力相对应的实现。因此这不是“支持性细节”层面的偏差，而是代码实际用途与声明主要功能明显不一致，属于显著描述-行为不匹配。
声明描述的是一个面向小红书数据采集与分析的完整技能，但提供的代码片段仅是一个本地辅助函数：读取当前项目 package.json 的 name 字段并做缓存。该行为既不涉及声明中的外部平台访问，也不包含任何搜索、抓取、评论处理、聚类、情感分析或需求洞察逻辑。虽然这可能是项目内部的支持性实现，但就当前代码片段本身而言，其实际行为与声明目的没有直接对应关系，因此应判定为明显不匹配。
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'"
Without declared permissions the skill's intent is opaque and cannot be validated.
The file forces a specific language/locale for all user-facing descriptions, examples, and operational guidance. Under the policy, language constraints should either be user-selectable or clearly justified as region-specific; this file does not explicitly provide either accommodation or opt-in.
The natural-language description and keywords are entirely in Chinese and centered on the Xiaohongshu platform, with no indication that users can opt into another language or locale. Under the policy, forcing a specific language or locale without explicit opt-in is a natural-language policy concern.
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
This JavaScript file contains natural-language documentation entirely in Chinese, including the module description and parameter docs, with no indication that the skill supports other languages or that Chinese is a justified regional requirement. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
This code emits user-facing status and error messages only in Chinese, including validation errors and success/failure notices. The file does not indicate that the skill is region-specific or that users can choose their preferred language, which creates a natural-language locale policy concern.
This code constructs outbound HTTPS GET and POST requests and includes a TOKEN header plus serialized request parameters/body, which can transmit user or system data to an external service. There is no confirmation prompt, logging, comment, or docstring in this file disclosing that network transmission and credential use occur.
This JavaScript file contains multiple user-facing validation and error messages exclusively in Chinese, such as the doc comment and calls to utils.printError. Because the skill does not offer a language choice or document that it is intentionally limited to a Chinese-speaking context, it creates a natural-language locale policy issue under the language/locale rule.
This code reads the GUAIKEI_API_TOKEN from the environment, sends the note URL and query parameters to remote comment APIs, and then writes the returned results to a local JSON file. While there are status messages and help text, there is no clear user-facing warning that request data is transmitted to an external service and that fetched comment data will be persisted locally.
Detected: suspicious.exposed_secret_literal