ICS Anomaly Detection — ML monitoring for OT/ICS environments (Modbus/DNP3/OPC UA)
Defensive security: detect anomalies in industrial control systems with machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic analysis — flag deviations, rogue devices, and historian mismatches for OT security teams
- What
- Defensive security: detect anomalies in industrial control systems with machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic analysis — flag deviations, rogue devices, and historian mismatches for OT security teams
- Cost
- Free
- Needs
- passive network monitoring sensors on OT network SPAN/TAP ports; 2–4 weeks of baseline traffic capture during normal operations; Python 3.9+ with scikit-learn, numpy, pandas; process historian access; understanding of normal operational patterns (shift changes, batch processes, maintenance windows)
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @mukul975's detecting-anomalies-in-industrial-control-systems skill, listed here with credit to its creator (authored by mahipal, purely defensive OT/ICS security): deploy anomaly detection for operational-technology environments using machine learning on OT network baselines. It walks the agent through building multi-dimensional baseline models of deterministic SCADA communications (timing, protocol behavior, network topology), combining them with physics-based process models and Modbus/DNP3/OPC UA traffic analysis, to flag deviations, rogue devices, and mismatches against historian data — with use cases like baselining deterministic SCADA polling, complementing signature-based IDS in OT, and investigating alerts from platforms like Nozomi Guardian or Dragos that need deeper protocol analysis. Mapped to MITRE ATT&CK, NIST CSF, and NIST AI RMF frameworks. Honest caveats: a SPECIALIZED skill — it assumes OT network access (SPAN/TAP on OT segments, 2–4 weeks of baseline capture, historian access) and process knowledge; it explicitly does not replace process safety systems (SIS); the ML models detect deviations, they don't identify exploits. Apache-2.0 licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
ICS Anomaly Detection is a free Muse skill for purely defensive OT and ICS security. It detects anomalies in industrial control systems with machine learning on OT network baselines, physics-based process models, and Modbus, DNP3 and OPC UA traffic analysis, flagging deviations, rogue devices and historian mismatches for OT security teams.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 54a7988Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: passive network monitoring sensors on OT network SPAN/TAP ports; 2–4 weeks of baseline traffic capture during normal operations; Python 3.9+ with scikit-learn, numpy, pandas; process historian access; understanding of normal operational patterns (shift changes, batch processes, maintenance windows) Install "ICS Anomaly Detection — ML monitoring for OT/ICS environments (Modbus/DNP3/OPC UA)" for me. It gives my agent @mukul975's defensive OT anomaly-detection workflow: build multi-dimensional baselines of deterministic SCADA communications (timing, protocol behavior, topology), combine them with physics-based process models and Modbus/DNP3/OPC UA traffic analysis, and flag deviations, rogue devices, and historian mismatches — with mappings to MITRE ATT&CK, NIST CSF, and NIST AI RMF. Apache-2.0 licensed. Repository: https://raw.githubusercontent.com/mukul975/anthropic-cybersecurity-skills/54a798831d2266a3ca61ce68a7acb80b81160d57/skills/detecting-anomalies-in-industrial-control-systems/SKILL.md Pinned version: install the code at commit 54a798831d2266a3ca61ce68a7acb80b81160d57 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "detecting-anomalies-in-industrial-control-systems". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. confirm SPAN/TAP coverage of my OT segments; arrange 2–4 weeks of baseline capture; get process historian access; do NOT use this as a replacement for safety instrumented systems). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 54a7988 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
ICS security
By the same creator, in the same series:
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.