ClawHub

EzyHost

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed EzyHost API skill for managing hosted sites, with powerful account actions that fit its purpose but require careful user confirmation.

Install this only if you want an agent to manage your EzyHost account through an API key. Use a dedicated revocable key, verify project IDs before changes, and require explicit confirmation for deleting projects or files, rolling back versions, changing teams/domains/API keys, or exporting captured emails.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents a destructive project-deletion endpoint and states it cannot be undone, but it does not instruct the agent to require explicit user confirmation before invoking it. In an agent setting, this increases the risk of accidental or prompt-induced destructive actions that irreversibly delete hosted content and associated files.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The rollback operation overwrites the current project files with a prior snapshot, but the documentation lacks a warning that this is a destructive state-changing action. An agent could be induced to restore an old version and silently discard newer work without an explicit confirmation checkpoint.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill exposes email collection, listing, export, and deletion capabilities without privacy, consent, or data-handling guidance. This is risky because an agent may facilitate collection or exfiltration of personal data without ensuring lawful consent, least-privilege use, or user awareness.

VirusTotal

50/50 vendors flagged this skill as clean.

View on VirusTotal