ClawHub
Back to skill

Security audit

三峰智能

Security checks across malware telemetry and agentic risk

Overview

This is a coherent smart-home control skill with sensitive but disclosed device-control and token-storage behavior.

Before installing, understand that this skill can control real smart-home devices and execute existing scenes after login. Use it only for the intended 三峰 smart-home account, and review the stored local state if you later want to remove access by logging out or deleting the skill state.

SkillSpector

By NVIDIA
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 (1)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger description includes broad everyday phrasing such as references to home/device lists, status queries, and control requests without a narrowly scoped invocation boundary. In a smart-home control skill, over-broad triggering can cause the agent to invoke this skill on ambiguous user messages and perform or prepare sensitive physical-world actions in the wrong context.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.