ClawHub
Back to skill

Security audit

Reference Checker Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a reference-checking instruction skill that asks the agent to verify academic citations using appropriate scholarly sources, with no hidden code or credential use found.

Install only if you want an agent to help verify manuscript references. Expect it to use web or database searches where available, and manually review any references it marks as Critical, Major, or Manual check, especially when paywalled Chinese databases are involved.

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.