Back to skill

Security audit

IceCube ZSXQ Community

Security checks across malware telemetry and agentic risk

Overview

This is a Chinese-language paid-community operations guide with somewhat broad trigger wording, but it does not install code, request credentials, or perform actions itself.

Install this if you specifically want Chinese-market 知识星球/zsxq or paid-community operations guidance. Review any separate browser/API tools before giving them login sessions, posting authority, or payment-related access, because this skill itself only gives guidance but points to workflows that could involve real accounts.

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
89% confidence
Finding
The trigger description uses broad keywords such as '知识星球', '会员制', and '付费社区', which can cause the skill to activate in many unrelated conversations. Over-broad invocation increases the chance of inappropriate routing, unwanted commercialization behavior, or the agent steering users into this monetization workflow when they did not intend to use it.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.