ClawHub
Back to skill

Security audit

易学导师

Security checks across malware telemetry and agentic risk

Overview

This is a text-only 易学 interpretation skill with broad but disclosed domain triggers and no executable code or hidden system access.

Install only if you want an 易学/divination-style interpretive assistant. Avoid sharing unnecessary sensitive health, relationship, birth, career, or location details, keep any prediction records under your control, and do not rely on it for medical, legal, financial, or mental-health decisions.

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
94% confidence
Finding
The trigger list is very broad and includes many common terms such as 易学、八卦、风水、易经、科学解构 and related concepts that can appear in ordinary cultural, historical, or academic discussion. This can cause unintended invocation of the skill in contexts where the user did not ask for divination-style interpretation, increasing the chance of irrelevant or misleading guidance and accidental collection of sensitive contextual details during the skill's clarification flow.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.