ClawHub
Back to skill

Security audit

Mihomo Proxy Management

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is a coherent Mihomo proxy admin helper, but users should confirm disruptive proxy actions before running them.

Install this only if you want an agent to administer your Mihomo instance. Keep the API secret private, prefer localhost or a trusted host, and ask the agent to confirm before switching nodes, closing connections, flushing caches, reloading configuration, upgrading, or restarting the service.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad enough to activate on generic mentions of 'clash', 'proxy', or proxy switching without clearly requiring explicit intent to manage a mihomo instance. That can cause the agent to surface or execute network-control actions in contexts where the user did not clearly ask for administrative operations, increasing the chance of unintended system changes.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill includes destructive operations like closing all connections, reloading configuration, flushing caches, and restarting the service, but does not instruct the agent to warn the user about disruption or obtain confirmation first. In practice, this can terminate active traffic, interrupt service, and create availability issues from an ambiguous or accidental request.

Static analysis

No suspicious patterns detected.