ClawHub
Back to skill

Security audit

Permission Guard

Security checks for vulnerabilities and agentic risk

Overview

This skill is an instruction-only permission guard that describes safety checks for commands without adding hidden code, installs, or data export.

Before installing, review how any future implementation writes permission rules, especially auto-allow and 'don't ask again' behavior. Keep bypass mode disabled outside tests and require explicit approval before saving broad command permissions.

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.