ClawHub
Back to skill

Security audit

Wangyangming Think Partner

Security checks across malware telemetry and agentic risk

Overview

This is a text-only philosophy coaching skill with no code or system access, though users should treat it as reflective guidance rather than professional advice.

Install only if you want a Wang Yangming/心学 lens for reflection and motivation. Do not rely on it for mental-health crises, legal, medical, HR, or safety-critical decisions, and ask your agent for a different framework when that philosophical framing is not appropriate.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation conditions are very broad, everyday self-help phrases that can match a wide range of unrelated user conversations. This can cause the skill to trigger outside its intended context, steering users into unsolicited philosophical or quasi-therapeutic guidance and displacing more appropriate assistance.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The per-model trigger questions are ambiguous and map common feelings like confusion, pressure, unfairness, or uncertainty to a fixed ideological framework. Because these are nonspecific states, the skill may activate unreliably and over-apply moralized advice in contexts where the user did not ask for that lens, increasing the risk of misleading or inappropriate guidance.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.