ClawHub
Back to skill

Security audit

继承纠纷举证质证要点

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Chinese inheritance-dispute evidence assistant with no executable code, persistence, or hidden data handling.

Before installing, understand that this skill is meant for legal work and may require you to provide sensitive inheritance, family, property, medical, and litigation facts. It should be used as drafting and analysis support, with current law and original evidence reviewed by a qualified lawyer.

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
90% confidence
Finding
The default prompt invokes the skill via a broad activation phrase without any gating conditions, scope checks, or requirement that the user explicitly request inheritance-litigation assistance. An underspecified trigger can cause the skill to activate in loosely related legal conversations, increasing the chance of over-collection of sensitive facts, off-topic legal guidance, or unintended use in contexts where specialized evidence analysis was not requested.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.