Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add trilwu/secskills --skill testing-ics-ot-protocolsgit clone --depth 1 https://github.com/trilwu/secskillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/trilwu/secskills/testing-ics-ot-protocols)<a href="https://agentmods.dev/skills/trilwu/secskills/testing-ics-ot-protocols"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/testing-ics-ot-protocols.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 114 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00077 | $0.03575 |
| Opus 5 | $0.00039 | $0.01788 |
| Sonnet 5 | $0.00015 | $0.00715 |
| Haiku 4.5 | $0.00008 | $0.00358 |
Grade A, and why
testing-ics-ot-protocols scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Testing ICS/OT Protocols
ICS/OT protocols were designed for reliability in isolated networks, not security on connected ones. Most have no authentication, no encryption, and no integrity checking. The danger is not that they are hard to exploit — it is that exploitation can have physical consequences, which is why safety constraints govern everything you do here.
When to Use
- Assessing SCADA networks or ICS environments during an authorized engagement
- Testing Modbus, DNP3, OPC UA, BACnet, EtherNet/IP, S7comm, or MQTT devices in scope
- Performing an ICS-specific penetration test with OT safety requirements
- Reviewing OT network segmentation and Purdue model compliance
- Evaluating remote access pathways into control system networks
- Inventorying ICS assets and identifying unauthenticated protocol exposure
When NOT to Use
- Standard IT network scanning — use
enumerating-network-services - HMI web interfaces tested as regular web apps — use
testing-web-applications - Writing ICS-specific detection rules — use
engineering-detections
Safety-First Principles
OT pentesting is not IT pentesting with different ports. The rules of engagement are fundamentally different because the targets control physical processes.
Why active scanning is dangerous in OT:
- PLCs and RTUs run minimal embedded firmware. A malformed packet or unexpected connection can crash the device, halt a process, or cause it to fail to a dangerous state.
- Restarting a PLC may require physical access, and the process it controls may not tolerate interruption.
- Some devices interpret any TCP connection as a command session — connecting is acting.
- Nmap's default service probes have crashed PLCs in production environments.
Mandatory constraints:
- Always have an OT engineer or plant operator present or on immediate call during active testing.
- Obtain written authorization that explicitly covers ICS/OT assets — general network pentest scope does not imply OT scope.
- Test in maintenance windows whenever possible. Never test safety-instrumented systems (SIS) without explicit, separate authorization.
- Start with passive observation. Move to active enumeration only after the passive phase confirms device types and the OT engineer approves.
- Distinguish read-only operations (reading registers, querying device info) from write operations (setting coils, writing registers, issuing commands). Write operations require per-device approval.
- Have a rollback plan for every write operation. Know the expected state before you change anything.
- Document every interaction with every device, including timestamps and the exact commands sent.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 349 lines · 77 tokens per session scan A 895da03d5edc
testing-ics-ot-protocols is a skill published in the GitHub repository trilwu/secskills (137 stars, last pushed 4d ago), licensed MIT. It adds 77 tokens to every session and 3,575 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cardputer-buddy
Iterate on the Cardputer-Adv MicroPython app bundle (Claude Buddy, Snake, Hello) after the device is already provisioned via m5-onboard. Use when the user wants to add a new app, push a single changed .py without re-flashing, watch device serial logs, or run a one-shot REPL command. Trigger on "add an app", "push to…
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
google-cloud-filestore-autoscale
Inspects Google Cloud Filestore capacity and utilization, evaluates storage scaling rules, and performs capacity autoscaling (scale UP for low free space or scale DOWN for cost optimization). Use when monitoring Filestore instance headroom, resizing instance shares, configuring automated growth/shrink thresholds…
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.
gke-ai-troubleshooting-tpu-dynamic-slices-monitoring
Monitors, troubleshoots, and manages GKE TPU Dynamic Slices custom resources. Use when checking TPU slice lifecycle states, troubleshooting slice provisioning failures, validating single-slice or multi-slice (JobSet) workload manifests, or safely patching stuck finalizers and disabling the slice controller. Don't use…
gke-ai-troubleshooting-tpu-vbar-oom
Diagnoses and prevents vbarcontrolagent segfaults, out-of-memory (OOM) errors, and TPU device initialization failures on TPU v6e nodes in GKE caused by race conditions during TPU device resets or high-frequency metrics polling. Use when troubleshooting vbarcontrolagent crashes, memory cgroup OOMs in serial console…