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 Encod3d-Sec/TORCH --skill hunt-icsgit clone --depth 1 https://github.com/Encod3d-Sec/TORCHWrote 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/encod3d-sec/torch/hunt-ics)<a href="https://agentmods.dev/skills/encod3d-sec/torch/hunt-ics"><img src="https://agentmods.dev/badge/skills/encod3d-sec/torch/hunt-ics.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to critical
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 →
- critical Prompt Injection · line 12 This content may contain harmful instructions that could cause physical harm if followed. CRITICAL: Review carefully before use.Fix: Remove all content that could lead to harmful outcomes. Add safety guardrails and human oversight for any high-risk operations.
- high YARA Match · line 32 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 | $0.00094 | $0.02060 |
| Opus 5 | $0.00047 | $0.01030 |
| Sonnet 5 | $0.00019 | $0.00412 |
| Haiku 4.5 | $0.00009 | $0.00206 |
Grade A, and why
hunt-ics 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hunt: ICS / SCADA / OT
Assumes hunt-core for the scope gate, two-account rule, confirmation gate, enumeration limits, stop conditions, wiki protocol, FIND output, and Deadends. Do not re-derive any of that here.
SAFETY - hard stop, overrides everything below
Writing to a live PLC moves real machinery: it can over-pressure a vessel, over-speed a motor, or disable a safety interlock, and so damage equipment or injure and kill people. Only ever drive a process toward a dangerous state on a target that is EXPLICITLY an authorized lab or CTF simulation. Never on a real plant, and never when scope carries no_dos/passive_only - there OT is READ-ONLY (FC1-4), never write (FC5/6/15/16). The instant the objective is met (e.g. the flag the HMI/CCTV reveals is in hand), STOP writing and revert any coil/register you changed if you can. This is a hard stop and it outranks every other note in this file.
Wiki
qmd_query "ICS SCADA OT Modbus S7comm EtherNet/IP DNP3 OpenPLC Node-RED PLC HMI coil holding register" via wiki-search MCP
Hub: [[network-moc]] (live index). Primary page: [[ics-scada-modbus]]. Payload arsenal: wiki/payloads/modbus.md.
Anchors: [[iot-attacks]], [[firmware-hardware]].
Attack surface (ranked by exploitation value)
- Modbus / TCP 502 - no auth, no session, trivially readable AND writable. The primary lever: FC1-4 read coils/registers, FC5/6/15/16 write them. Highest value, highest danger.
- OpenPLC web (8080) and Node-RED (1880, dashboard
/ui) - the SCADA/IT side that drives the PLC. OpenPLC routes/programs /monitoring /hardware /users; authed OpenPLC = upload-program RCE. Node-RED/uisocket.io config NAMES the registers. - HMI web app (Flask/Werkzeug with an
/api/...live-state endpoint) - not itself the lever but the ORACLE that tells you whether a write landed. - S7comm / TCP 102 (S7/iso-tsap) -
python-snap7db_readfor creds/flags in data blocks. - EtherNet/IP 44818, DNP3 20000, then BACnet 47808/udp, Fox 1911/4911, OPC-UA 4840 - enumerate with the matching nmap scripts; less commonly the CTF lever, but map them.
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.
- 8d ago First seen · 79 lines · 94 tokens per session scan A a96d20b93787
hunt-ics is a skill published in the GitHub repository Encod3d-Sec/TORCH (314 stars, last pushed 6d ago), licensed MIT. It adds 94 tokens to every session and 2,060 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.