Security audit
Security checks for vulnerabilities and agentic risk
This skill coherently fetches user-requested public Xiaohongshu data through a disclosed third-party API and saves local result logs, with no evidence of hidden execution, persistence, or destructive behavior.
Install only if you are comfortable sending Xiaohongshu keywords or links and your GUAIKEI_API_TOKEN to guaikei.com, and remember that returned comments and metrics are saved locally in temp logs; use it only for public data you are authorized to analyze.
声明描述的是一个面向小红书数据采集与分析的技能，但提供的代码片段仅是通用命令行参数解析与帮助文本生成模块。它处理参数读取、重复参数检测、类型校验、位置参数冲突告警、必填参数检查和帮助文案输出，不访问网络、不处理小红书链接、不抓取任何作品/评论/互动数据，也不做横向对比分析。按照评估标准，这属于代码实际行为与声明主目的明显不一致，应判定为 mismatch。
The declared description promises substantial Xiaohongshu-related capabilities: searching content, retrieving creator/post metrics, and analyzing comments. The supplied code chunk does none of these things. It merely reads package.json from the local filesystem and returns the package name, caching the result. This is a materially different behavior from the declared purpose and indicates a clear mismatch. While this could be a small supporting utility within a larger codebase, based on the supplied code chunk alone, the actual behavior shown is unrelated to the described external data retrieval and analysis functionality.
The declared description describes a full Xiaohongshu data acquisition and analytics tool. However, the supplied code chunk is merely a utility module for terminal output formatting and logging. There is no evidence of network access, scraping, API calls, data extraction, comment retrieval, structured data transformation, or analysis logic. This is a material description-to-behavior mismatch for the provided code chunk.
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 manifest description, examples, and the full SKILL.md content consistently require Chinese comprehension, which effectively forces a specific language for users and agents. The file does not state that the skill is region- or language-specific, nor does it offer an alternative language option or user opt-in.
The README instructs users to interact with the agent by 'directly speaking plain language' and gives only a Chinese-language example command. Combined with the entirely Chinese-facing description, this indicates a language-specific interaction expectation without documenting user choice or opt-in, which matches the locale/language policy concern.
The changelog title and all content are written only in Chinese, which indicates a language-specific presentation. Under the policy, forcing a specific language without user opt-in or documented justification 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
The document explicitly guides users to retrieve comment content and blogger interaction metrics from a third-party social platform, but it provides no warning about privacy, terms-of-service, consent, or data protection obligations. That omission can normalize collection of personal or user-generated data without appropriate legal or policy checks, increasing the risk of misuse or non-compliant data handling.
This file contains user-facing natural-language instructions solely in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-only audience. Under the language/locale policy, forcing a specific language without user opt-in is a policy concern.
This code contains user-facing strings only in Chinese, including warnings and status messages, with no indication that the skill is region-specific or that users can opt into another language. That can violate a language/locale policy requiring user choice or documented justification.
Detected: suspicious.exposed_secret_literal