ClawHub
Back to skill

Security audit

小红书数据分析 SocialDataX 笔记搜索

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed read-only Xiaohongshu/XHS search skill that uses a SocialDataX API key and sends search terms to that service.

Install this only if you want SocialDataX-backed Xiaohongshu/XHS research. Treat searches as third-party API calls using your SOCIALDATAX_API_KEY, and clarify with the agent before use when a request is generic research rather than explicitly XHS/RedNote-focused.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill’s trigger text is broad enough to activate on many generic research or trend-analysis requests, which can cause the agent to invoke this external skill when the user did not specifically ask for Xiaohongshu/XHS data. That can lead to unnecessary third-party data disclosure in queries, over-collection, and unintended use of an API-backed external service, even though the skill itself is read-only.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.