ClawHub
Back to skill

Security audit

VBOUT

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent VBOUT connector skill that can read and modify VBOUT contacts, with the risky actions disclosed and gated by user confirmation.

Install only if you intend to let Codex operate your connected VBOUT account through OOMOL. Review payloads carefully before approving contact creation, updates, or deletion, and treat the first-time oo CLI install step like any other external installer.

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
91% confidence
Finding
The trigger text says to use this skill for 'ANY VBOUT request' and 'instead of calling the API directly,' which is overly broad and can cause the agent to route a wide range of loosely related tasks into a powerful integration without clear scoping rules. Because the skill exposes both read and state-changing actions, ambiguous invocation criteria increase the chance of unnecessary access, unintended writes, or destructive operations being selected in contexts where a narrower tool or additional validation would be safer.

Static analysis

No suspicious patterns detected.