ClawHub
Back to skill

Security audit

Life Hacks Helper

Security checks across malware telemetry and agentic risk

Overview

This is a household-advice skill made of markdown guidance only, with no code, credentials, network access, or persistence.

Install this if you want a Chinese-language household tips helper. Be aware it may activate on broad daily-life how-to questions, and treat cleaning and food-storage advice as general guidance: follow product labels, avoid mixing cleaners, and use official safety guidance for high-risk situations.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
93% confidence
Finding
The trigger description is broad enough to match very common everyday queries such as generic 'how to' questions, which can cause the skill to activate outside its intended domain. Overbroad routing can hijack unrelated user requests, leading to incorrect handling, degraded assistant behavior, and possible interference with safer or more appropriate skills.

Natural-Language Policy Violations

Medium
Confidence
90% confidence
Finding
The skill metadata and operating instructions strongly prescribe Chinese-language behavior without stating that it should adapt to the user's language. This can override user preference or system language expectations, causing misrouting or unusable responses for users who did not opt into Chinese, and can reduce reliability in multilingual environments.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.