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.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
High
Do not use without reviewing
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.
The `<potential_matches>` section is empty, so I reviewed the full skill content directly. - **Touchlink master key (SKILL.md line 51):** `0x9F5595F10257C8A469CBF42BC93FEE31` is a literal, 32-character hexadecimal value with high-entropy appearance. It functions as a credential for Touchlink commissioning, and the document presents it as the value to use. It is a publicly documented constant from the Zigbee Light Link specification and the cited research, so it is not a secret in the strict sense of a private, per-deployment credential. It is still a literal, usable key of the type this scan targets, and the recall-first override applies, so I am flagging it. - **`ZigBeeAlliance09` (line 84):** This is a low-entropy, well-known default trust center link key, closer to the simple-word setup values the policy excludes. Not flagged. - **Tool commands, URLs, and `<addr>`/`<PANID>`/`<ch>` placeholders:** These are instructions or template variables, not credentials. Not flagged. No private keys, live API tokens, or complex user passwords are present. The only candidate is the Touchlink master key, which is a judgment call: it is public, but it is a literal high-entropy value that works as a credential.
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.
The skill's setup instructs `git clone https://github.com/IoTsec/Z3sec` and then executes its `z3sec_inter_pan.py` script, so executable code is fetched and run; the publisher is an academic research GitHub organization rather than a recognized vendor or foundation, and no integrity check is shown, making it a common/reputable unofficial dependency (medium), while the other links are static references.
SnailSploit/Claude-Red
fd81441
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.