ClawHub
Back to skill

Security audit

追加被执行人申请书生成器

Security checks across malware telemetry and agentic risk

Overview

This skill is a legal document drafting aid with some overbroad trigger and self-approval language, but no code, persistence, credential use, or hidden system access was found.

Before installing, treat this as a drafting assistant rather than verified legal advice. Narrow or confirm activation when discussing general financial distress, ignore the self-approval labels, and review any generated court filing with current law and a qualified legal professional before use.

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
84% confidence
Finding
The trigger list includes broad, everyday phrases such as "公司没钱" that can match ordinary conversations about financial distress rather than a clear request for this legal-execution workflow. That increases the chance of unintended activation, which can inject legal-procedure content into unrelated contexts and cause privacy, compliance, or user-trust issues. The surrounding metadata also contains self-attesting labels like "NOT Suspicious", "CLEAN", and "安全版本", which should not be relied on and slightly increase suspicion rather than reduce it.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.