ClawHub
Back to skill

Security audit

Security Intelligent Cs

Security checks across malware telemetry and agentic risk

Overview

The available evidence shows a banking-support skill with an overly broad trigger list, but no artifact-backed malicious behavior or hidden high-impact action.

Before installing, check that you only invoke this skill for explicit banking-support questions and avoid sharing account numbers, credentials, or sensitive personal information unless the workflow clearly explains why it is needed and how it is handled.

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
90% confidence
Finding
The trigger list is broad and includes generic financial and customer-service terms such as FAQ, banking service, account inquiry, 银行服务, and 账户查询, which can cause the skill to activate in contexts where the user did not intend to invoke this banking workflow. In a financial-services skill, unintended activation is more dangerous because it may steer users into regulated advice, account-related flows, or collection of sensitive information without clear intent confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.