Wittgenstein Master

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Chinese-language conversational analysis style with no evidence of code execution, credential access, persistence, or destructive behavior.

Reasonable to install if you want a Chinese-language philosophical conversation aid. Be aware that the trigger phrase may be easy to say accidentally, and the skill may respond in Chinese even when that is not your preferred language.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
82% confidence
Finding
The trigger phrase "我们争的是什么" is short, generic, and could plausibly appear in ordinary user conversation unrelated to explicitly invoking this skill. That means the skill may activate unexpectedly and steer the interaction into its constrained Wittgenstein-style behavior, causing unintended prompt routing or response hijacking rather than direct code-execution risk.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The entire skill is authored in Chinese and defines responses, triggers, and examples only in Chinese, without offering user language preference or fallback behavior. In a multilingual environment this can override user expectations, degrade usability, and create prompt-routing confusion if the skill activates for users who did not consent to a Chinese-only interaction style.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal