ClawHub

China Tax Law

Security checks across malware telemetry and agentic risk

Overview

This is a text-only China tax-law reference skill with no code execution or hidden access, though users should verify legal and tax guidance before relying on it.

Install only if you want help researching PRC tax-law topics. Treat outputs as informational, verify current rules with official sources, and consult a qualified tax professional for filings, planning, disputes, or high-value decisions.

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 (2)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill description is broad enough to trigger on a wide range of tax-, legal-, and compliance-related prompts without clear boundaries, which can cause inappropriate routing or overuse of this skill. In a legal/tax domain, over-broad invocation is more dangerous because users may receive jurisdiction-specific or professional-style guidance in contexts where the skill is not actually appropriate, increasing the risk of incorrect advice and unsafe automation.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
The skill is written to operate in Chinese without offering a language choice or documenting that Chinese is required due to the source-law domain. While not directly a security exploit, this can cause user misunderstanding, hidden assumptions, and incorrect handling of multilingual prompts or translated legal materials. The domain context makes this somewhat less dangerous because Chinese tax law is naturally tied to Chinese-language authorities, but the lack of explicit language-handling rules still creates reliability and misuse risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal