CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

offensive-zigbee-thread-matter

Zigbee, Thread, and Matter mesh-protocol attack methodology — IEEE 802.15.4 sniffing with TI CC2531 / CC2540 / Sonoff Zigbee Dongle E, KillerBee toolkit, Touchlink commissioning abuse with the well-known transport key, replay/injection attacks, Zigbee Cluster Library command abuse for door locks and bulbs, Thread network credential theft, Matter commissioning chain analysis, and 6LoWPAN/IPv6 routing exploitation. Use when targeting smart-home or commercial mesh deployments, Zigbee-based door locks, lighting, or sensor networks.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

High

Do not use without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-sectioned, command-rich body that gives an operator concrete entry points for Zigbee, Thread, and Matter attacks. Its main weaknesses are the absence of validation checkpoints for destructive operations (capping workflow clarity), one elided code example, and no progressive disclosure structure in a 165-line single file.

Suggestions

Add explicit validation checkpoints to the workflow, e.g., 'Confirm the pcap contains the transport-key-encrypted network key before attempting recovery' and 'Verify the recovered network key decrypts existing captures in Wireshark before injecting ZCL commands' — required because factory_reset_request and device-theft steps are destructive.

Replace the elided scapy frame 'Dot15d4FCS()/Dot15d4Data()/ZigbeeNWK(...)/ZigbeeAppDataPayload(...)/ZCLDoorLock(...)' with a complete, executable frame construction including real field values (source/destination addresses, profile, cluster, sequence).

Move the Thread and Matter sections and the hardware table into separate reference files (e.g., references/thread-matter.md, references/hardware.md) and keep SKILL.md as a lean overview pointing to them.

DimensionReasoningScore

Conciseness

The body is largely lean and command-driven with little padding, but a few sentences restate background Claude already knows (e.g., 'Matter unifies Zigbee/Thread/Wi-Fi device onboarding under one commissioning model', the opening mesh-protocol overview), which could be trimmed. It is noticeably above the 'mostly efficient' midpoint anchor, fitting 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Mostly executable guidance: zbstumbler/zbdump/zbid, z3sec commands with real flags, and scapy imports are concrete and runnable. However, the flagship ZCL door-lock frame is elided ('ZigbeeNWK(...)/ZigbeeAppDataPayload(...)/ZCLDoorLock(...)') and cheatsheet step 5 says only '(custom scapy-dot15d4 + zbee_nwk frames)', which are gaps that keep it below fully copy-paste ready.

4 / 5

Workflow Clarity

The sequence is clearly laid out twice (Quick Workflow and the numbered Engagement Cheatsheet), but there are no validation or verification checkpoints anywhere — e.g., confirming the captured join exchange actually contains the encrypted network key before attempting decryption, or verifying the recovered key decrypts traffic before issuing ZCL commands. The rubric caps destructive/batch workflows without validation at 3, and this skill's core steps include factory resets and device theft.

3 / 5

Progressive Disclosure

The single file has clear section headers, but at ~165 lines everything is inline — hardware tables, Thread and Matter specifics, the Touchlink derivation detail, and a references list — with no bundle files or split references, so content that could live in separate files is inlined and organization is only partially realized.

3 / 5

Total

14

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it names a clear niche, lists numerous concrete capabilities with specific hardware and tooling, and closes with an explicit 'Use when...' trigger clause. The only minor gap is a few missing natural synonym phrases.

DimensionReasoningScore

Specificity

The description enumerates many concrete, specific actions — 'IEEE 802.15.4 sniffing with TI CC2531 / CC2540 / Sonoff Zigbee Dongle E', 'Touchlink commissioning abuse', 'replay/injection attacks', 'ZCL command abuse for door locks and bulbs', 'Thread network credential theft', 'Matter commissioning chain analysis', '6LoWPAN/IPv6 routing exploitation' — covering the full attack methodology comprehensively, matching the anchor for multiple specific concrete actions.

5 / 5

Completeness

It clearly answers 'what' (detailed enumeration of attack capabilities) and 'when' with an explicit trigger clause: 'Use when targeting smart-home or commercial mesh deployments, Zigbee-based door locks, lighting, or sensor networks.'

5 / 5

Trigger Term Quality

Natural terms users would say are well covered — 'Zigbee', 'Thread', 'Matter', 'smart-home', 'door locks', 'lighting', 'sensor networks', 'mesh' — but a few common variations such as 'home automation' or 'IoT' phrasing are absent, placing it just below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The Zigbee/Thread/Matter mesh-protocol attack niche is distinct with protocol-specific trigger terms (Zigbee, Thread, Matter, mesh), so it is unlikely to fire for unrelated skills; only trivial overlap with a general wireless/offensive skill exists.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

SnailSploit/Claude-Red

Path

Skills/wireless/offensive-zigbee-thread-matter/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.