Skip to content

Zigbee, Thread & Matter Attacks

Guides an agent through offensive testing of Zigbee, Thread and Matter smart-home radio networks

Stars
10,230
Licence
MIT
Files
1 file

What it does

This is a playbook that teaches an AI agent how to attack the wireless mesh protocols used by many smart-home devices such as bulbs, door locks and sensors. It covers sniffing radio traffic with cheap dongles, abusing Zigbee's Touchlink pairing feature with a publicly known key, capturing network keys during device joins, and replaying or injecting control commands. It also outlines attack ideas against Thread and Matter onboarding.

Great for

  • Security researchers authorised to test smart-home or commercial IoT deployments
  • Penetration testers preparing a written-scope wireless assessment
  • Students learning how 802.15.4 protocol weaknesses work in a lab

Skip it if

  • Attacking devices or networks you do not own or have written permission to test, since the steps describe factory-resetting, hijacking and unlocking devices and this is illegal in most places
  • Home users wanting to secure their own smart home, because it gives attack steps and no hardening or defensive guidance
  • Beginners without radio hardware or protocol background, since the instructions assume familiarity with KillerBee, scapy and Wireshark

Try asking

  • “Walk me through sniffing Zigbee channel 11 with a CC2531 and KillerBee for an authorised lab test”
  • “Outline how Touchlink commissioning abuse could be tested against the bulbs in our client's office”
  • “Explain how a Thread PSKc leak from a companion app could be assessed during a pentest”
  • “Build a checklist for auditing Matter commissioning windows on our test devices”
Step-by-step guide: how to use Zigbee, Thread & Matter AttacksInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    offensive-zigbee-thread-matter.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip offensive-zigbee-thread-matter.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip offensive-zigbee-thread-matter.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

  • Only use this against hardware and networks you own or are contracted to test, and record written authorisation first
  • Ask the agent to focus on defensive detection and hardening steps if you are a homeowner or defender, as the file itself contains little of that
  • Verify tool commands and GitHub repositories yourself before running them, since the skill gives snippets without testing them

What's inside

  • SKILL.md

Redistributed unmodified from SnailSploit/Claude-Red 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.