ClawHub

AgentDomains

Security checks across malware telemetry and agentic risk

Overview

AgentDomains is a coherent domain-management helper, but it can create persistent public hostnames and stores a reusable API key locally.

Install only if you want an agent to manage public AgentDomains hostnames. Review commands before claiming, forwarding, delegating, or deleting names; do not expose admin/debug/private services; and protect or rotate the stored API key when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The manifest description is broadly scoped and recommends use whenever an agent builds a website, API, webhook URL, or needs a stable public address. That kind of generic trigger can cause the skill to activate in many common development situations, increasing the chance an agent exposes infrastructure or modifies DNS without a clear, user-confirmed need.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The documentation states that signup saves an API key to ~/.agentdomains/config.json but does not warn about local secret storage, file permissions, or the sensitivity of that credential. This can lead users or downstream agents to leave reusable credentials on disk insecurely, where they may be exposed to other local users, logs, backups, or later prompts/tools.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly encourages exposing local or development servers to the internet but does not include a warning about the security consequences of public exposure. Publishing a dev service or webhook endpoint can unintentionally expose unauthenticated admin panels, debug routes, sensitive APIs, or unpatched software to attack from the public internet.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal