Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Xiaohongshu data-analysis command tool that uses a third-party API token and saves local result logs, with no evidence of hidden or destructive behavior.
Install only if you are comfortable sending Xiaohongshu keywords or URLs, plus your GUAIKEI_API_TOKEN, to guaikei.com and storing returned public-content results in local temp logs. Use it for public Xiaohongshu analysis only, avoid private or sensitive data collection, and review any retained logs if the results may contain personal comments or creator information.
声明描述的是一个面向小红书/xhs/rednote 的数据获取与达人匹配分析技能，核心能力应涉及外部平台内容检索、页面/接口访问、数据提取和分析。但提供的代码仅是 args.js，实现了通用 CLI 参数解析和帮助文本生成，包括读取 flag 值、校验数字类型、处理别名、位置参数、默认值、重复参数和帮助输出。这属于基础工具代码，不体现任何与小红书、达人筛选、内容分析或市场调研相关的实际行为。根据给定代码片段，其真实用途与声明用途存在明显且实质性的偏差。
声明描述的是一个面向小红书达人筛选、内容分析和市场调研的完整数据能力集合；但给定代码片段仅访问本地文件系统，读取 package.json 中的 name 字段并做缓存。这不是对声明能力的直接实现，也不是明显支撑这些能力的业务逻辑，而是一个与技能元数据相关的通用辅助函数。依据“当代码具有 materially different primary purpose”应判定为不匹配：该代码的实际目的与声明的主要功能严重不一致。
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 description is broadly scoped around influencer matching, market research, data lookup, competitor monitoring, and public-opinion analysis, which can cause the skill to activate on many generic social-media analytics requests without clear guardrails. Over-broad routing can expose users to unintended data collection or scraping workflows and increase the chance the agent uses this skill in contexts where a narrower or safer tool should be selected.
The natural-language trigger examples for keyword search are broad enough that routine user phrasing could invoke the skill without sufficiently explicit intent or required parameters. Overbroad trigger guidance increases the chance of unintended data collection or execution in response to ambiguous requests.
The note-detail trigger example is too generic and does not explicitly bind execution to the presence of a valid note URL. This can cause the skill to activate on loosely related analysis requests and then prompt for or infer inputs in ways the user did not clearly authorize.
The document describes scraping notes, comments, and creator interaction metrics, but it lacks warnings about privacy, platform terms, lawful use, and data-handling expectations. In a data-collection skill, omission of these safeguards increases the risk of misuse, non-compliant collection, and inappropriate handling of potentially personal data.
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 blogger-post query examples include broad monitoring language like competitor monitoring and theme tracking without crisp activation boundaries. In a tool that scrapes public account activity, vague triggers can lead to unintended surveillance-style collection beyond the user's original request.
The comment-query trigger examples are broad and do not clearly state that a note link is mandatory. This makes accidental activation more likely and can encourage follow-up collection of comment data from a target the user has not unambiguously identified.
The documentation states that using any capability requires configuring the GUAIKEI_API_TOKEN, which conflicts with the skill metadata claim that it works without login/account. This mismatch can cause hidden credential prompts, break trust boundaries, and lead operators to supply secrets they did not expect the skill to need.
Detected: suspicious.exposed_secret_literal