ClawHub
Back to skill

Security audit

Iru (Kandji)

Security checks across malware telemetry and agentic risk

Overview

This is a coherent read-only Kandji connector skill with disclosed setup steps and no evidence of hidden, destructive, or exfiltrating behavior.

Before installing, confirm you trust OOMOL and want this agent to use your connected Kandji account for read-only blueprint and user lookups. Review the `oo` CLI install and account-connection flow if it is not already set up, and avoid using this skill for Kandji changes unless a future version clearly lists those actions and asks for explicit confirmation.

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
87% confidence
Finding
The skill description directs the agent to use this skill for ANY Kandji-related request, which is broader than the actual safe scope described later in the file. Overly broad routing can cause unintended invocation, mis-handle tasks outside the implemented read-only actions, and steer agents away from more appropriate or constrained handling paths.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.