Security audit
Security checks for vulnerabilities and agentic risk
This skill appears purpose-built for Xiaohongshu research, but it handles API tokens and token-bearing links in ways users should review before installing.
Install only if you are comfortable sending Xiaohongshu queries, URLs, and your Guaikei API token to the provider. Avoid printing the token, rotate it if it has been exposed, and regularly delete or protect the generated `logs/` directory because it can retain research history and token-bearing links.
src/utils/request.js:79API Credential Transmitted in URL Query Strings
SKILL.md:208Troubleshooting Instructions Reveal the Complete API Token
src/xiaohongshu/detail-cli.js:138Token-Bearing URLs and Complete Results Are Automatically Persisted in Plaintext
The skill states that every execution is automatically archived under logs/, which means fetched note, comment, or creator data is persisted locally by default. Silent retention of potentially sensitive research data increases exposure to later unauthorized access, accidental sharing, or over-retention, especially when users may assume the tool only returns transient JSON.
The skill states that every execution is automatically archived under logs/, which means fetched note, comment, or creator data is persisted locally by default. Silent retention of potentially sensitive research data increases exposure to later unauthorized access, accidental sharing, or over-retention, especially when users may assume the tool only returns transient JSON.
The skill states that every execution is automatically archived under logs/, which means fetched note, comment, or creator data is persisted locally by default. Silent retention of potentially sensitive research data increases exposure to later unauthorized access, accidental sharing, or over-retention, especially when users may assume the tool only returns transient JSON.
The skill states that every execution is automatically archived under logs/, which means fetched note, comment, or creator data is persisted locally by default. Silent retention of potentially sensitive research data increases exposure to later unauthorized access, accidental sharing, or over-retention, especially when users may assume the tool only returns transient JSON.
Referenced artifact was not completely inspected
- "分析这条小红书笔记评论区的主要观点和负面反馈: node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 100"
Referenced artifact was not completely inspected
- "分析这条小红书笔记评论区的主要观点和负面反馈: node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 100"
Referenced artifact was not completely inspected
- "分析这条小红书笔记评论区的主要观点和负面反馈: node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 100"
Referenced artifact was not completely inspected
- "分析这条小红书笔记评论区的主要观点和负面反馈: node src/xiaohongshu/comment-cli.js --url 'https://www.xiaohongshu.com/explore/xxx?xsec_token=yyy' --limit 100"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 20 条作品都在发什么: node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 20"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 20 条作品都在发什么: node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 20"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 20 条作品都在发什么: node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 20"
Referenced artifact was not completely inspected
- "看这个小红书博主最近 20 条作品都在发什么: node src/xiaohongshu/post-cli.js --url 'https://www.xiaohongshu.com/user/profile/xxx?xsec_token=yyy' --limit 20"
Referenced artifact was not completely inspected
| 看某篇笔记的详情+评论 | `src/xiaohongshu/detail-cli.js` | 笔记 URL | `explore/` 或短链 |
Referenced artifact was not completely inspected
| 看某篇笔记的详情+评论 | `src/xiaohongshu/detail-cli.js` | 笔记 URL | `explore/` 或短链 |
Referenced artifact was not completely inspected
| 看某篇笔记的详情+评论 | `src/xiaohongshu/detail-cli.js` | 笔记 URL | `explore/` 或短链 |
The skill declares use of an environment variable (GUAIKEI_API_TOKEN) but does not declare any explicit tool scope or permission boundary. That weakens reviewability and least-privilege enforcement, making it easier for a skill to access secrets without clear user or platform visibility.
The documentation explicitly says results are automatically saved to logs/ but does not provide a prominent warning, consent mechanism, or retention policy. Because the skill handles user-supplied URLs, keywords, comments, and creator-monitoring data, undisclosed local persistence can expose business research, personal data, or regulated content to anyone with later access to the machine or workspace.
The README presents all user-facing instructions, warnings, and examples exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in or documenting a justified locale restriction is a natural-language policy violation.
This function sends a user-provided note URL and an API token to a remote API via postJson, but the file contains only developer-oriented docstrings and retry error logs, not any user-facing disclosure or confirmation. Because this is a code file performing network transmission of potentially sensitive user and credential data, it meets the missing-warning criterion.
This function performs a remote getJson request containing the API token, target URL, and limit parameters, yet there is no visible user-facing warning in the file that these values are sent off-host. Retry logging is present, but it does not disclose the privacy or data-transfer behavior to the user.
This code sends the provided API token as part of outbound HTTP requests when creating a search task. Although the function comments describe the parameter, there is no user-facing warning, confirmation, or disclosure that sensitive credential material will be transmitted to an external service.
This function performs an outbound HTTP request containing the API token and user-supplied search keyword and filters. The code has internal doc comments and retry error logging, but no visible user disclosure that user-provided query data and credentials are transmitted externally.
The user-facing strings are entirely in Chinese and the file provides no indication that the skill is China-specific or that users can opt into another language. Under the policy, hard-coding a specific language without user choice or documented justification is a natural-language policy violation.
This code emits user-facing error text in Chinese only, and later also prints a Chinese success message. The policy explicitly disallows forcing a specific language without user opt-in, and there is no indication here of locale selection or a documented region-specific constraint.
The success and failure messages shown to users are hard-coded in Chinese. Because the file provides no mechanism for language preference or opt-in, this is a natural-language locale policy violation under the stated rules.
No suspicious patterns detected.