clash-verge-auto-switch

• Outcome: Pass
• Latest audit: May 29, 2026, 8:29 PM
• Version:
  1.0.0

Overview

This skill does what it claims: tests local Clash/Mihomo proxy nodes, switches selector groups, and optionally installs a user-level macOS schedule for that same task.

Install only if you want Codex to control your Clash/Mihomo selector choices. Start with --dry-run or --list-groups, keep the controller local or trusted, protect any controller secret, and run the uninstall script when you no longer want scheduled switching.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Rogue Agent: Self-Modification, Session Persistence
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill clearly instructs the agent to execute local scripts, read from the user's home directory, interact with the Clash controller over the network, and install/remove launchd jobs, yet it declares no permissions. That mismatch weakens user awareness and policy enforcement, because a consumer of the skill cannot accurately assess that it can run shell commands, access files, and make persistent system changes.

Session Persistence

Medium

• Category: Rogue Agent

Content

1. Check whether the Mihomo controller is reachable.
2. If the user did not name target groups, inspect the live `/proxies` tree and auto-discover groups from the current active selection chain.
3. Expand `url-test`, `fallback`, and `load-balance` groups into leaf proxies, but do not rewrite nested selector groups unless the user explicitly targets them.
4. Test candidate proxies with the controller delay API and switch the selector group to the lowest-latency healthy node.
5. Report the winning node, measured latency, and whether a switch happened.

• Confidence: 70% confidence
• Finding: write nested selector groups unless the user explicitly targets them. 4. Test candidate proxies with the controller delay API and switch the selector group to the lowest-latency healthy node. 5. Repor

VirusTotal

66/66 vendors flagged this skill as clean.