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.
67
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
4 findings: 2 critical severity, 2 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E005: Suspicious download URL detected in skill instructions.
What this means
Detected a suspicious URL in the skill instructions that could lead the agent to download and execute malicious scripts or binaries. This includes links to executables from untrusted sources, typosquatting of official packages, URL shorteners that obscure the destination, and personal file hosting services.
Why it was flagged
Both URLs point to GitHub-hosted offensive toolkits/documentation (including a repository explicitly cloned and executed in the skill), which are untrusted code that can enable remote attacks—downloading and running such repos from unknown authors is high risk.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This document is an offensive how-to that explicitly instructs capturing keys, stealing/forcing devices into attacker networks, remote factory-resets, replay/injection of control commands (including unlocking locks), and credential theft—clearly enabling malicious, unauthorized access and data exfiltration.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The prompt embeds explicit cryptographic keys/passphrases (the Touchlink transport key and the default trust-center key) and instructs using them to join/decrypt networks, which requires the model to include secret values verbatim in outputs.
W008: Secret detected in skill content (API keys, tokens, passwords).
What this means
Detected sensitive credentials directly embedded within the skill content, such as API keys, access tokens, private keys, or service-specific secrets. Secrets should never be hardcoded in plain text within skill instructions.
Why it was flagged
I scanned the SKILL.md content for literal, usable credentials. Flagged: - The Touchlink "well-known transport key" 0x9F559A553B7A6B2C5C4FBB4E84956F3D (SKILL.md:45-47) is a high-entropy hex key and a real, usable credential for Touchlink commissioning. - The older default trust center link key "ZigBeeAlliance09" (SKILL.md:70-71) is a literal, known default key used to access/decrypt legacy Zigbee 1.x networks. No documentation placeholders or obvious example-only values were present that would be ignored. Both values are direct, usable credentials in the document, so I treat them as secrets to report.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W012: Unverifiable external dependency detected (runtime URL that controls agent).
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
The skill contains a runtime fetch-and-execute sequence—"git clone https://github.com/IoTsec/Z3sec" followed by running python z3sec_inter_pan.py—so remote repository code is fetched during runtime and then executed.
- Repository
- SnailSploit/Claude-Red
- Commit
24d7968
- Audited
- Security analysis
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.