ClawHub
Back to skill

Security audit

China Work Calendar

Security checks across malware telemetry and agentic risk

Overview

This is a simple local China holiday and workday calculator with no evidence of credential access, network use, persistence, or hidden behavior.

Reasonable to install as a local calendar utility. Use it for informational workday and holiday calculations, but verify important payroll, HR, legal, or travel decisions against official Chinese government notices because the holiday data is embedded and may become outdated or contain inaccuracies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger scope is broad enough to activate on general China holiday, workday, overtime, or vacation-planning queries, which can cause the skill to intercept requests outside a narrowly defined intent. This is dangerous because over-broad activation can lead to incorrect tool routing, unexpected behavior, and user confusion, especially when the skill only covers 2024-2027 data and may answer with incomplete or outdated information.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill content is written entirely in Chinese and the description strongly implies Chinese-language behavior without stating that responses should follow the user's language preference. This is risky because the skill may override the assistant's normal language-matching behavior, degrading usability and potentially causing misunderstandings for users who ask in another language.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.