ClawHub
Back to skill

Security audit

Hallucination Detector

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only skill for checking AI text against local sources, with no executable code or hidden behavior found.

Before installing, be comfortable with the agent reading the workspace documents and source code needed to verify claims. Run it in a scoped project if the repository contains sensitive material; no evidence shows external transmission, persistence, or credential access.

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.