ClawHub
Back to skill

Security audit

AI协作写作方法论

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only writing workflow skill that does not install code or request sensitive system access.

This appears safe to install as a writing helper. Be mindful that following its workflow may involve pasting drafts, business context, or research material into other AI or search tools, so avoid sharing confidential content unless those tools are approved for that data.

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.