ClawHub
Back to skill

Security audit

MOCO

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only MOCO connector helper that routes MOCO lookups through the OOMOL CLI, with no evidence of hidden data collection or destructive behavior.

Install this if you want Codex to read MOCO profile, company, and contact data through your OOMOL-connected account. Review the oo CLI installer before running first-time setup, and require explicit approval before any future version adds write or destructive MOCO actions.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The skill description instructs the agent to use this skill for ANY MOCO-related request instead of calling the API directly, which is an overly broad trigger. Broad routing increases the chance the skill is invoked in situations it was not narrowly designed for, including contexts where direct API use, stricter policy checks, or more specialized handling would be safer or more appropriate.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal