ClawHub
Back to skill

Security audit

Schopenhauer Wisdom

Security checks across malware telemetry and agentic risk

Overview

This appears to be a low-risk wisdom/philosophy skill with only a minor activation-scope concern and no evidence of malware, hidden persistence, credential access, or destructive behavior.

Install if you want this skill available for explicit Chinese-language wisdom/philosophy prompts. If your agent auto-activates skills from natural language, prefer invoking it deliberately so ordinary discussion about the phrase does not route into the skill unintentionally.

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
95% confidence
Finding
The skill declares a very broad natural-language activation phrase ("加载 人生的智慧") that could be triggered during ordinary discussion about loading or using this skill, rather than through a clearly namespaced command only. In agent environments where user text is continuously parsed for skill activation, this can cause unintended invocation, context switching, or execution of skill-defined behavior without the user explicitly intending to activate it.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal