ClawHub
Back to skill

Security audit

ntfy

Security checks across malware telemetry and agentic risk

Overview

This skill is a small ntfy integration that uses OOMOL's oo CLI for account reads and notification publishing, with write actions disclosed and requiring confirmation.

Before installing, be comfortable using OOMOL as the credential broker for ntfy. Let read-only account checks run only when relevant, and confirm the exact topic, message, and payload before any publish_message action. Review the oo CLI install command if the CLI is not already installed.

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
91% confidence
Finding
The skill description says to use this skill for ANY ntfy request and whenever a task involves ntfy, which creates an overly broad routing trigger. That can cause the agent to invoke this skill on incidental mentions of ntfy or without considering safer or more appropriate alternatives, increasing the chance of unintended external actions or unnecessary account-data access.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.