ClawHub
Back to skill

Security audit

MQTT

Security checks for vulnerabilities and agentic risk

Overview

This MQTT connector skill is purpose-aligned and clearly labels its write action, with no hidden persistence or unrelated data access found.

Before installing, be comfortable using OOMOL as the broker-facing connector and confirm MQTT publish requests carefully, especially topic, payload, encoding, and target environment. The CLI installer and account connection steps should only be used when needed for setup.

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
93% confidence
Finding
The trigger text is overly broad: "Use this skill for ANY MQTT request" and "Whenever a task involves MQTT, use this skill instead of calling the API directly" can cause the agent to route all MQTT-related tasks through this skill without adequate task-specific scrutiny. That increases the chance of unintended invocation of write-capable actions such as `publish_message`, especially because the skill includes both read and state-changing operations.

Static analysis

No suspicious patterns detected.