guaikei·小红书趋势脉搏

• Outcome: Review
• Latest audit: Aug 13, 2026 · 4:29 AM UTC
• Version: 1.0.0

Overview

This skill is a public Xiaohongshu data lookup tool whose network use, token requirement, and local result logging are mostly disclosed and fit its stated purpose.

Before installing, confirm you are comfortable sending Xiaohongshu keywords, URLs, and a GUAIKEI API token to guaikei.com, and periodically clean or protect the local logs directory because it can contain saved research results, URLs, comments, and creator metadata.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger text explicitly says the skill should be used even when the user only mentions `rednote/xhs` or provides a link, which can cause over-broad invocation without confirming user intent. That increases the chance of unintended data access, unnecessary third-party API calls using a secret token, and accidental handling of links the user did not want analyzed through this skill.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The README states that all task results are automatically saved to the local `logs/` directory, but the finding indicates this behavior is not clearly warned about in the skill description presented to users. Automatically persisting fetched public content, URLs, keywords, and analysis outputs can expose sensitive business research, user queries, or regulated data in shared or unmanaged environments.

Missing User Warnings

Low

• Confidence: 73% confidence
• Finding: The error message discloses the exact secret name (GUAIKEI_API_TOKEN) and includes a personal WeChat contact number in runtime error handling. This can leak operational details to end users, aid attackers in fingerprinting the integration, and creates an unnecessary social-engineering and supply-chain trust risk by directing users to an off-platform personal contact for credential issues.

Missing User Warnings

Medium

• Confidence: 84% confidence
• Finding: The CLI persists the full fetched detail response to a local JSON file automatically, and note details/comments may contain personal data, creator metadata, or other sensitive content. Because this happens without an explicit opt-in or warning at the point of execution, users may unintentionally leave recoverable local copies on disk, increasing privacy and data-handling risk.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The script persists full search output to a local JSON file derived from user input without explicit consent or an obvious opt-in. Even though the content is from public Xiaohongshu data, the saved file can retain sensitive queries, harvested result sets, and activity history on disk, creating unintended data exposure on shared systems or in agent workspaces.

VirusTotal

64/64 vendors flagged this skill as clean.

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:16