Clawhub Skill Bandwidth Income

Security checks across malware telemetry and agentic risk

Overview

This skill has a coherent purpose, but it deploys persistent bandwidth-sharing and VPN exit-node containers that can expose your IP, credentials, and network reputation with limited guardrails.

Install only on a dedicated machine or isolated VLAN after checking your ISP, platform terms, and local legal risk. Review and pin Docker images before use, avoid storing passwords directly in command history or compose files, and require explicit confirmation before setup all, monitor start, or any restart action.

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
82% confidence
Finding
The skill exposes generic command triggers like "setup", "status", "monitor", and "restart" without any namespace, target scoping, or safety constraints. In an agent ecosystem, overly broad triggers can be invoked unintentionally or collide with other skills, causing sensitive actions such as process restarts or shell-based setup routines to run in the wrong context.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal