ClawHub
Back to skill

Security audit

冰璃视角

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only roleplay skill for a fictional game character and does not contain code, credential access, or hidden system actions.

Install this if you want an immersive Bingli-style perspective. For legal, medical, financial, safety-critical, or source-grounded questions, explicitly ask the assistant to exit character mode or answer normally.

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.