ClawHub
Back to skill

Security audit

jasontest

Security checks for vulnerabilities and agentic risk

Overview

This is a small Qwen-VL prompt-formatting helper with no evidence of credential use, network access, persistence, or destructive behavior.

Reasonable to install for Qwen-VL prompt formatting. Treat any image URLs or prompt text you provide as content that may later be sent to the model or service you use with the generated prompt.

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.