ClawHub
Back to skill

Security audit

Data Analysis Zh

Security checks across malware telemetry and agentic risk

Overview

This is a simple Chinese data-analysis skill that only asks to read provided data and has no code, install commands, persistence, or hidden actions.

Install this for Chinese-language spreadsheet or business-data analysis workflows. Review sensitive datasets before sharing them with any agent, and be aware that broad data-analysis prompts may invoke this skill.

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
89% confidence
Finding
The skill description contains broad trigger phrases such as '帮我做数据分析' and '这份数据有什么规律', which can match a wide range of ordinary user requests. This increases the chance the skill is invoked unintentionally, causing overbroad routing of user queries and unnecessary exposure of potentially sensitive business data to this skill's workflow.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.