ClawHub
Back to skill

Security audit

劳动法维权技能库（8卡套装）

Security checks across malware telemetry and agentic risk

Overview

This appears to be a coherent labor-contract guidance skill, with only a minor risk that broad triggers could make it activate in loosely related employment conversations.

Before installing, treat the skill as legal-adjacent assistance rather than a substitute for a qualified labor lawyer. If you use it, consider narrowing activation or requiring confirmation before it gives contract-signing advice.

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 section uses broad situational descriptions like '准备签劳动合同' and '被告知试用期/竞业限制' rather than explicit invocation phrases. In an agent environment, this can cause accidental routing or over-triggering, leading the skill to activate in loosely related conversations and potentially provide legal guidance when the user did not clearly request it.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.