ClawHub
Back to skill

Security audit

中文公文写作

Security checks across malware telemetry and agentic risk

Overview

This skill is a scoped Chinese official-document writing aid with no evidence of hidden data access, persistence, or destructive behavior.

Install if you want help drafting or reviewing Chinese formal work documents. Treat generated legal, financial, procurement, audit, signature, seal, date, and official filing details as drafts requiring human verification, and run the lint script only on files you intentionally provide.

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
88% confidence
Finding
The example trigger phrase is broad enough that ordinary user requests such as '帮我起草一份项目请示' could cause the skill to activate in contexts where the user did not explicitly opt into this specialized behavior. That can lead to unintended routing, inappropriate formal-writing transformations, or suppression of safer/default behaviors in a broader agent system.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.