小红书热门笔记检索

• Outcome: Review
• Latest audit: Oct 4, 2026 · 4:20 AM UTC
• Version: 1.1.4

Overview

The skill is a disclosed Xiaohongshu public-data CLI that calls a third-party API with a configured token and saves local result logs; I found no hidden persistence, privilege escalation, destructive behavior, or unrelated data access.

Install this only if you are comfortable sending Xiaohongshu keywords or links, plus the GUAIKEI_API_TOKEN, to guaikei.com and having returned results stored in local temp logs. Avoid using it for private, login-only, or non-public content, and delete local logs if the research targets or comments are sensitive.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (49)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The declared description presents a full-featured Xiaohongshu data retrieval and analysis tool. However, the code chunk only implements generic command-line argument parsing and help-text generation. It does not access Xiaohongshu, perform searches, fetch any remote data, analyze notes/comments, or implement the four advertised capabilities. This is not merely a supporting detail tied to a larger visible feature implementation; based on the supplied code chunk, the observed behavior is materially different from the declared purpose.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 99% confidence

Finding

The declared description presents a full-featured Xiaohongshu analytics and search tool. The supplied code chunk does not implement any of those behaviors. Instead, it only accesses the local filesystem to read package.json and return the skill/package name. This is a materially different purpose and lacks all core declared capabilities, so it is a clear description-behavior mismatch.

Content

No source excerpt is available for this finding.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence

Finding

The supplied code does not implement any of the declared Xiaohongshu data collection or analysis capabilities. It only contains utility functions for printing a banner and formatted log messages to stderr. While such logging utilities could support a larger tool, this chunk by itself has a materially different behavior from the declared purpose and shows none of the advertised data access, scraping, search, or analysis functionality.

Content

No source excerpt is available for this finding.

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 124)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 137)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 284)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 287)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 290)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 293)May include surrounding context.

md

- "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"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md

- "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'"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 123)May include surrounding context.

md

- "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'"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 136)May include surrounding context.

md

- "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'"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

md

- "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'"

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 281)May include surrounding context.

md

- "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'"

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 81% confidence

Finding

The skill requires access to an environment variable (GUAIKEI_API_TOKEN) but does not declare an explicit tool scope or permissions boundary. That omission can cause the host agent to over-trust the skill and expose secrets or execution capabilities without a clear least-privilege contract, increasing the chance of unintended secret use or exfiltration.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The skill states that execution automatically archives results to local logs, but this persistence behavior is not prominently disclosed in the primary description or invocation warnings. Stored logs may contain sensitive research targets, monitored accounts, note URLs, or comment data, creating privacy and retention risk if users are unaware of local storage.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The invocation criteria are broad enough to trigger on ordinary conversational mentions of Xiaohongshu, including vague requests like '帮我看看 XX 在小红书上的情况'. Over-broad routing can cause the agent to call an external data service unnecessarily, sending user-supplied queries or links to a third party without sufficiently explicit user intent or data-minimization checks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The instruction tells users to '直接说人话' and provides only a Chinese example phrase for interacting with the agent, while the rest of the README is also entirely in Chinese. This can be read as imposing a specific language/locale on users without any opt-in or alternative, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Whitespace Padding

Medium

• Category: Prompt Injection
• Confidence: 70% confidence

Finding

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.

Content

Scanner excerpt · references/options.md (reported line 179)May include surrounding context.

md

| --------------- | ------------------------ | --------------------------------------------------------------------------------- |
| `--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

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

This markdown file contains user-facing troubleshooting instructions only 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 policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

This file contains natural-language strings in Chinese throughout comments, thrown errors, and generated help text. Under the stated policy, forcing a specific language without offering a language or locale choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

The strings shown to the user at L17-L18 and L22 are exclusively in Chinese, which imposes a specific language on all users. Under the policy, forcing a language without user opt-in or documented locale justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: SKILL.md:15