ClawHub
Back to skill

Security audit

Ethernetip Tap

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly scoped EtherNet/IP/PLC operations helper with disclosed high-risk write capability that is gated and off by default, though its approval variable name should be checked before use.

Before installing, confirm that the ot-aiops implementation actually enforces the documented approval gate for EtherNet/IP writes and consider renaming or standardizing the approval variable. Treat any live PLC write as change-controlled work: use dry-run first, verify the endpoint, and only apply with explicit authorization.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The write-governance instructions for an EtherNet/IP skill reference the approval variable `OPCUA_AUDIT_APPROVED_BY`, which appears to be copied from a different protocol. In an OT write path, this kind of control mismatch can cause operators to set the wrong gate, misunderstand whether approval is actually enforced, or accidentally bypass intended change-control procedures for live PLC writes.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.