ClawHub
Back to skill

Security audit

Universal Model Switcher

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only skill for choosing among existing models, with no code, secrets access, persistence, or hidden install behavior.

Before installing, confirm the named models exist in your environment and that broad task labels like code, reasoning, and chat match how you want model switching to work.

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.