ClawHub
Back to skill

Security audit

Pi-hole

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Pi-hole management skill, but it gives an agent broad Pi-hole admin capability through OOMOL, including changes and deletions that users should approve carefully.

Install only if you trust OOMOL with Pi-hole administration for the connected instance. Confirm exact payloads before any change, deletion, restore, DNS-blocking change, log flush, gravity update, or backup export, because these actions can affect network behavior or expose DNS activity and device information.

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 skill explicitly claims it should be used for ANY Pi-hole request, including read, write, and destructive operations, which creates an overly broad invocation scope. This increases the chance an agent will route sensitive or state-changing Pi-hole tasks through the skill without narrower intent checks or stronger confirmation boundaries, especially since the skill exposes destructive actions like deleting entries, importing backups, and changing DNS blocking state.

Static analysis

No suspicious patterns detected.