Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed command-line integration for querying public Xiaohongshu data through the GUAIKEI API, with no evidence of hidden execution, exfiltration, or destructive behavior.
Before installing, make sure you are comfortable using a third-party GUAIKEI API token and sending Xiaohongshu keywords or public URLs to guaikei.com. Use it only for public content analysis and keep the locally saved result logs in mind if the returned data is sensitive to your team.
声明描述的是一个面向小红书达人发现、筛选和复核的业务技能，核心能力应涉及平台内容搜索、数据抓取、互动指标分析和候选名单评估。实际代码仅是 src/utils/args.js，一个通用命令行参数解析器，处理 --help、flag/alias、默认值、必填校验、位置参数冲突和帮助文本生成等基础 CLI 功能。这类代码最多属于底层配套工具，但单独来看并不执行任何声明中的核心能力，也未访问或处理小红书相关资源。因此，描述与该代码块实际行为存在明显不匹配。
This code chunk does not implement any of the declared core capabilities. Its sole behavior is a small utility that reads package.json from the local filesystem and returns the package name. While this could be a harmless support helper in a larger project, the supplied chunk itself is unrelated to influencer discovery, content analysis, engagement metrics collection, or comment analysis on Xiaohongshu. Therefore, the description does not accurately represent what this code chunk actually does.
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 natural-language interface and operating instructions are presented only in Chinese, including the description, invocation guidance, and examples. Under the policy, forcing a specific language without user opt-in or a documented justification is a locale/language policy concern.
The description is entirely in Chinese, which constitutes a natural-language locale choice embedded in the skill metadata. The file does not indicate that the skill is region-specific or that users can opt into this language, so it may violate the policy against forcing a language without user choice.
The README instructs users to interact with the agent using a Chinese example phrase, '然后直接说人话', and the entire skill is presented as Chinese-only without any stated language options. This can violate a language/locale policy if users are expected to use the skill in a specific language without explicit opt-in or alternatives.
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 document instructs users to collect creator interaction metrics and note comments from an external platform without warning about privacy expectations, platform terms, or the fact that external requests and data collection are occurring. In a skill specifically designed for creator screening and comment analysis, this omission increases the chance of inappropriate scraping, misuse of personal data, or noncompliant collection workflows.
This file contains user-facing status/error strings only in Chinese ("警告..." and "已使用配置的私有TOKEN"). Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
Multiple natural-language strings in this file are fixed to Chinese, such as request failure and timeout messages. This enforces a specific language without any visible user opt-in or locale-selection mechanism, which fits the language/locale policy violation category.
This code emits all validation feedback in Chinese string literals, such as the error messages on L08, L13, L17, L21, L26, L59, L64, L69, and L73. Because the file provides no opt-in language selection or documented region-specific justification, it appears to force a specific language, which matches the locale policy violation criteria.
Detected: suspicious.exposed_secret_literal