ClawHub
Back to skill

Security audit

ClawHub

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese writing and research skill whose behavior matches its stated purpose and does not request special system access.

Install this if you want help drafting Chinese reports, summaries, study notes, or defensive security research digests. Treat any notes, chat logs, or documents you provide as visible to the agent, and verify current security claims and citations for important decisions.

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.