ClawHub

Clawhub Skill Bandwidth Income

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent about setting up bandwidth-income nodes, but it asks users to run persistent network-sharing and VPN-node containers with credentials, open ports, and elevated networking privileges.

Review carefully before installing. Use only on a dedicated machine or isolated network, verify and pin Docker images, avoid giving passwords to unofficial containers, read each provider's ToS and your ISP rules, and require explicit approval before any setup, monitoring, or restart action runs.

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)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill prominently instructs users to deploy bandwidth-sharing and VPN exit-node services, including a NET_ADMIN-capable Mysterium exit node and containers that expose the user's IP and network resources, while deferring risk disclosure until the end. This framing can cause users to run privacy-sensitive or abuse-prone services without understanding legal, reputational, ISP-policy, or network-abuse consequences, increasing the chance of unsafe deployment.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill exposes very broad command triggers (e.g. setup, status, monitor, restart) without any embedded constraints, scoping, or safety context in the manifest. Because the skill also declares access to exec and web_fetch, these generic triggers could map to powerful actions such as installing software, restarting services, or fetching remote content, increasing the chance of unsafe or unintended execution.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal