ClawHub
Back to skill

Security audit

Cubox

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Cubox connector wrapper that can save URLs after user confirmation, with no hidden code or persistence found.

Install only if you are comfortable connecting Cubox through OOMOL and using the oo CLI. Confirm the exact URL payload before any save action, and review the oo CLI installer before running first-time setup commands.

SkillSpector

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
88% confidence
Finding
The trigger phrase says to use this skill for "ANY Cubox request" and to prefer it over direct API access, which is broader than necessary and can cause over-activation. In an agent setting, overly broad routing increases the chance the skill is invoked for loosely related requests and may lead to unintended read/write operations through the connected Cubox account.

Static analysis

No suspicious patterns detected.