ClawHub
Back to skill

Security audit

Xunzi

Security checks for vulnerabilities and agentic risk

Overview

This is a persona-only Xunzi roleplay skill with no tools, code execution, credentials, persistence, or file access.

Safe to install as a roleplay prompt. Users should remember it is designed to answer in character as Xunzi and may not remind them that it is an AI persona.

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.