ClawHub
Back to skill

Security audit

Confucius

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Confucius roleplay skill with no code, tools, credentials, persistence, or data access.

Install this if you want an in-character Confucius-style conversation. Disable it when you need ordinary assistant behavior, current factual accuracy, explicit AI transparency, or advice in legal, medical, financial, or other high-stakes areas.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Static analysis

No suspicious patterns detected.