ClawHub
Back to skill

Security audit

Diting Labor Law Expert

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese labor-law guidance skill with no executable code, persistence, credential use, or hidden data handling.

Installers should understand this skill provides legal-adjacent analysis, not formal legal advice. For high-value employment decisions, local rules, current salary thresholds, or active disputes, verify against official sources and consult a licensed labor 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
91% confidence
Finding
The skill description contains a long mixed list of Chinese natural-language triggers ('Use when ...') spanning many adjacent HR/legal scenarios. This can cause over-broad routing or unintended activation for queries that only partially match, especially where topics border non-legal domains such as compensation, performance, or training. In a legal-adjacent skill, misrouting is risky because users may receive incomplete or inapplicable legal guidance instead of the correct specialist or a request for clarification.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.