ClawHub
Back to skill

Security audit

小红书-社媒运营专家 | 青虎AI

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Xiaohongshu/Rednote social-media research workflow that uses a specific external Qinghu API with user authorization, with minor cautions around tokens, paid calls, and automatic spreadsheet exports.

Before installing, be aware that this skill may ask for or use a Qinghu API token, call Qinghu data tools that can consume credits, and create local spreadsheet exports for larger datasets. Use it for Xiaohongshu research workflows where those behaviors are acceptable.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description uses mandatory activation language for a broad class of common Xiaohongshu requests, which can cause the agent to invoke this skill even when the user's intent is ambiguous or when a narrower/safer skill would be more appropriate. In practice this increases the chance of unnecessary external data access, token solicitation, and paid tool usage without strong relevance checks.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs the agent to automatically export large result sets to a file and provide a link without first obtaining user consent at the point of export. That can create unintended local file artifacts, expose sensitive or proprietary scraped data through links, and bypass user expectations about where data will be stored or shared.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.