ClawHub
Back to skill

Security audit

AI工作幻觉

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only alias that redirects Chinese search terms to the VeriClaw skill and does not request code execution, credentials, or local access.

Before installing, understand that this alias is not a standalone verification tool; it mainly routes matching Chinese phrases to the VeriClaw skill and public pages. Review the linked VeriClaw skill if you want the actual functionality.

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.