ClawHub
Back to skill

Security audit

Wu Wei (无为, Effortless Action)

Security checks across malware telemetry and agentic risk

Overview

This is a text-only coaching skill about applying wu wei/effortless action, with no code execution, credential use, persistence, or data access.

Before installing, be aware that this skill may be invoked by broad phrases like 'stop forcing' or 'let it happen.' It is best used for coaching, management, product, negotiation, or personal-practice situations where over-effort is the actual issue, and not for emergencies, safety-critical decisions, or domains where the user has not developed the underlying skill.

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 activation criteria include common, ambiguous phrases like 'let it happen' and 'stop forcing' that can appear in ordinary conversation unrelated to the skill's intended use. In an agentic system, this can cause accidental activation and steer responses toward a specific philosophical coaching frame when the user did not request it, reducing reliability and potentially misguiding decisions in sensitive contexts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.