ClawHub
Back to skill

Security audit

Mocean

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward Mocean connector wrapper, with SMS sending disclosed and gated by user confirmation.

Install this only if you use Mocean through OOMOL and are comfortable with agents running oo connector commands on your connected account. Review SMS payloads carefully before approval because sending messages can cost money and contact real recipients.

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
89% confidence
Finding
The description says to use this skill for ANY Mocean request and instead of calling the API directly, which creates an overly broad routing trigger. That can cause the agent to invoke this skill for loosely related Mocean tasks without sufficient task-specific validation, increasing the chance of unintended API reads or writes, especially because the skill includes a state-changing send_sms action.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.