ClawHub
Back to skill

Security audit

NamingExpert灵犀取名官

Security checks across malware telemetry and agentic risk

Overview

This is a coherent instruction-only naming assistant with no executable code, data access, persistence, or hidden high-impact behavior.

Safe to install for creative naming help. Be aware it may activate on short or ambiguous requests about names, and independently verify trademarks, domains, cultural meanings, and any sensitive personal or commercial details before using a suggested name publicly.

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
95% confidence
Finding
The trigger description explicitly says the skill should activate even for vague, everyday phrases like '帮我想个名字' and '取个好名'. This broad matching can cause unintended invocation in unrelated contexts, increasing the chance that the agent routes normal conversation to this skill when the user did not actually want structured naming assistance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.