Skip to content

OT / ICS Security Assessment

Guides authorized, passive-first security reviews of industrial control systems (PLCs, SCADA, OT networks).

Stars
43,969
Licence
MIT
Files
2 files

What it does

This is a set of written instructions that tells an AI agent how to carry out a security review of industrial control systems such as PLCs, SCADA and HMIs, the equipment that runs factories, utilities and similar sites. It pushes the agent to work passive-first: map network zones using the Purdue model, inventory assets, analyse captured traffic and exported configuration files offline, and only do light read-only checks when written authorization allows. It explicitly forbids writing to PLC registers or coils and high-rate scanning of production networks without clear permission, and asks for findings to describe physical or process impact.

Great for

  • Security professionals doing authorized assessments of OT/ICS environments
  • Engineers in lab or isolated test networks learning how industrial protocols can be checked safely
  • Teams that want a safety-first checklist before any active testing on industrial networks

Skip it if

  • Testing live production PLCs or safety systems without a signed scope, because mistakes can cause physical harm and outages
  • Anyone without written authorization for the target sites and networks, since the skill assumes legal, approved work
  • General IT or web application testing, which the skill itself says should not use ordinary web scanning defaults against OT

Try asking

  • “Map the Purdue zones and asset inventory for this plant network based on the passive capture I uploaded”
  • “Review the exported TIA Portal project file for default passwords and plaintext protocol risks, offline only”
  • “Write an authorized, read-only assessment plan for our Modbus and EtherNet/IP segment during a maintenance window”
  • “Summarise firmware version to CVE mapping for our controllers without flashing anything”
Step-by-step guide: how to use OT / ICS Security AssessmentInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    ot-ics.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip ot-ics.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip ot-ics.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Provide a written scope naming sites, network ranges and whether active scanning or register writes are allowed before the agent starts; the skill expects this.
  • Start with offline inputs such as PCAP files and exported configurations, which are the lowest-risk way to use it.
  • Have a qualified OT engineer review any recommended active step, and run tests only in an isolated lab or during an approved maintenance window.

What's inside

  • references/ot-safe-assessment.md
  • SKILL.md

Redistributed unmodified from zhaoxuya520/reverse-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.