ClawHub
Back to skill

Security audit

exe-dev

Security checks across malware telemetry and agentic risk

Overview

This skill is a transparent command reference for managing exe.dev VMs, including public sharing actions that users should confirm carefully.

Install this as a command reference, not as permission for automatic infrastructure changes. Before running commands that create VMs, make services public, change ports, add users, generate share links, or configure domains, confirm the exact VM, exposed service, intended audience, authentication state, and any cost or data exposure impact.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill provides one-line commands to create VMs, make them public, change exposed ports, and share access, but it does not pair those actions with concrete security warnings, authentication expectations, or least-exposure guidance. In a skill meant to guide agent actions, this can easily lead to accidental internet exposure of development services, admin panels, or other sensitive workloads.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.