Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently provides user-invoked Xiaohongshu public-data lookup commands through a disclosed third-party API, with no evidence of hidden execution, exfiltration, or destructive behavior.
Install only if you are comfortable using guaikei.com as the data provider and storing run results locally in temp logs. Treat GUAIKEI_API_TOKEN like a secret, avoid running it on private or non-public Xiaohongshu content, and clear local logs if keywords, URLs, comments, or business research should not persist on the machine.
代码仅包含 parseArgs、readValueAfterFlag 和 buildHelp 三个通用 CLI 辅助函数，用于处理命令行选项、报错和生成帮助信息。它既没有网络请求、也没有访问小红书资源、也没有任何数据分析或内容策略输出逻辑。因此其实际行为与声明的核心用途存在明显且实质性的偏差。这不属于正常的底层支撑细节，因为当前代码片段本身的功能完全是通用参数处理，而非声明中的任一业务能力实现。
The declared description promises external social-media data collection and analysis capabilities for Xiaohongshu content. However, the supplied code does not access Xiaohongshu, perform network requests, parse notes/comments, compute engagement metrics, or generate analysis. Its sole purpose is writing log content to local temp-directory files. While logging can be a supporting detail, this chunk by itself materially differs from the declared primary purpose and introduces filesystem write behavior that is not reflected in the description or permissions.
There is a clear mismatch between the declared purpose and the actual code. The description promises a feature-rich Xiaohongshu data collection and analysis skill, but the supplied code chunk is only a utility function for reading the package name from a local package.json file. This behavior is unrelated to the declared capabilities and does not implement any of the stated social media search, scraping, detail fetching, comment analysis, or reporting functions.
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 declares use of a sensitive environment variable (GUAIKEI_API_TOKEN) but does not define an explicit tool scope such as permissions or allowed-tools. In agent environments, missing scope declarations can let the skill run with broader-than-necessary ambient capabilities, reducing reviewability and increasing the blast radius if later code or prompts are modified.
The trigger guidance says the skill should be called when a user says phrases like '帮我看看 XX 在小红书上的情况', which is broad conversational language and could overlap with many loosely related requests. Although surrounding bullets add some context, this example lacks tighter boundaries or negative examples for when such phrasing should not invoke the skill.
The README states that execution results are automatically archived locally, but it does not clearly warn users that those logs may contain searched keywords, queried URLs with tokens or identifiers, and returned public data. This can lead to unintended retention and later disclosure of potentially sensitive business research activity or personal data in local files, especially on shared machines or in synced directories.
This markdown file applies to SQP-2, and it instructs users to obtain interaction metrics such as follower, like, and favorite counts, as well as comments later in the document, but it does not include any warning about privacy, platform terms, or responsible handling of collected social-media data. Because the skill behavior affects third-party data and could have privacy implications, the description should disclose that clearly to users.
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 troubleshooting document presents all user-facing guidance exclusively in Chinese, which can violate a language/locale policy when no user opt-in or alternative language is offered. The file does not indicate that the skill is intentionally region-specific or that users may choose another language.
This JavaScript file uses Chinese-only natural-language comments, parameter descriptions, error text, and retry messages, indicating the skill is designed around a single language/locale. Under the policy rule, forcing a specific language without offering user choice or documenting a justified locale restriction is a natural-language policy concern.
This code uses Chinese-only natural-language strings in comments, error messages, and generated help output, which effectively forces a specific language for users. The policy allows locale constraints only when users are given a choice or the regional limitation is explicitly justified, neither of which appears in this file.
Detected: suspicious.exposed_secret_literal