Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Xiaohongshu public-data lookup tool that uses a third-party API token and saves results locally, with no evidence of hidden or destructive behavior.
Install only if you are comfortable using guaikei.com as the data provider, sending it your Xiaohongshu query URLs or keywords along with GUAIKEI_API_TOKEN, and having returned public-data results archived in local temp logs. Avoid using it for private, login-only, or regulated data.
该代码片段仅实现了通用参数解析器（parseArgs、readValueAfterFlag、buildHelp），用于处理命令行选项、位置参数、默认值、帮助信息和输入校验。这属于基础支撑工具，但当前提供的代码本身没有任何与小红书/xhs/rednote 相关的数据源访问、API 调用、网页抓取、内容分析、达人筛选或市场分析逻辑。由于评估的是“声明描述是否准确代表所提供代码块实际行为”，而该代码块的实际行为是 CLI 工具层面的参数处理，和声明的核心用途存在明显偏离，因此应判定为不匹配。
声明描述的是一个面向小红书数据检索与分析的完整技能，但给出的代码片段只是一个本地工具函数：通过 fs 读取 package.json 并返回其中的 name 字段，同时做了简单缓存。该行为与宣称的核心用途没有直接对应关系，也未体现任何网络访问、数据抓取、内容分析、筛选排序或评论处理逻辑。虽然这可能是技能内部的辅助实现文件，但就该代码片段本身而言，其实际行为与声明用途明显不一致，因此应判定为 mismatch。
The declared description presents a full-featured Xiaohongshu data intelligence and influencer-analysis skill. However, the provided code chunk contains only generic logging helpers and a banner printer. There is no evidence of network access, API calls, scraping, parsing, query handling, filtering, analytics, or any interaction with Xiaohongshu resources. This is therefore a strong description-behavior mismatch for the supplied code chunk. While this file could be a minor supporting utility within a larger project, based strictly on the provided code, the actual behavior does not substantiate the declared capabilities.
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 invocation rules say to call the skill whenever a user mentions Xiaohongshu and wants to '查看、搜索、分析内容' or says broad phrases like '帮我看看 XX 在小红书上的情况'. These conditions are expansive enough to capture many ordinary requests and do not provide clear scope limits or exclusion examples beyond a few high-level 'do not call' cases.
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 code emits user-visible status and warning text only in Chinese ("警告..." and "已使用配置的私有TOKEN"). The file provides no indication that the skill is region-specific or that users can opt into this locale, which can violate language/locale policy requirements.
This code sends request parameters, JSON payloads, and a TOKEN header to a remote host via HTTPS in both postJson and getJson. There is no confirmation prompt, user-facing log, or warning in this file indicating that user or system data may be transmitted off-box.
The comments and all user-facing validation/error messages in this file are written only in Chinese, which imposes a specific language on users without any visible opt-in or locale-selection mechanism. Under the policy, forcing a language without user choice is a natural-language policy violation unless the locale restriction is explicitly justified.
The help text explicitly requires GUAIKEI_API_TOKEN, and the code reads it from process.env before performing the comment task. While an API token may be an implementation detail, this capability is in tension with the manifest's statement that no account login is needed, because the tool still depends on external credentials to function.
The CLI persists fetched comment results to a local JSON file via log.taskWrite, but the skill description emphasizes retrieval/analysis behavior and does not disclose local retention. Comment data can contain personal or sensitive user-generated content, so silent persistence increases the risk of unintended disclosure, over-retention, and secondary access by other local users or processes.
Detected: suspicious.exposed_secret_literal