ClawHub
Back to skill

Security audit

Chinese Tech Writing

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Chinese technical writing helper with no hidden execution, data access, persistence, or credential handling found.

Install this when you want Chinese technical-writing review or rewrite assistance. Be aware that broad document-writing prompts may activate it, so use clearer wording when you want another language or a non-technical writing style.

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
91% confidence
Finding
The trigger conditions are very broad and include generic phrases such as '帮我写文档', '文档检查', and 'rewrite', which can cause the skill to activate for many ordinary requests beyond narrowly scoped Chinese technical-writing tasks. Over-broad activation can hijack routing, override more appropriate skills, or impose this skill’s behavior in contexts the user did not intend, reducing reliability and potentially causing unsafe instruction precedence in multi-skill systems.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The skill description frames the assistant as a Chinese technical-writing helper and lists broad activation terms without stating that Chinese-only behavior requires user choice. If automatically applied, this can override user language preference and constrain output format or language unexpectedly, which is a form of instruction overreach and can degrade correctness, accessibility, and user control.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.