ClawHub
Back to skill

Security audit

Xueqiu

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is for summarizing public Xueqiu posts and quote pages, with explicit limits against trading, account actions, API reverse engineering, and bulk scraping.

Install only if you want an agent to summarize public Xueqiu pages. Keep use limited to public posts and quote pages, avoid logged-in or account actions, do not use it for trading orders or investment decisions, and avoid high-volume scraping or API reverse engineering.

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
86% confidence
Finding
The invocation description is broad enough to match many generic Xueqiu-related requests, which can cause the skill to activate outside narrowly intended use cases. In a web-automation context, over-broad routing increases the chance of unnecessary browsing, data extraction, or interaction with a finance-related site where tighter scope is important.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.