z-wave
Z-Wave S0 network-key derivation flaw exploitation, S2 ECDH/DSK analysis, replay attacks against unauthenticated Z-Wave nodes, traffic capture with RTL-SDR, and active fuzzing/replay with EZ-Wave and Z-Force. Covers 868.42 MHz (EU) and 908.42 MHz (US) bands.
62
73%
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
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/iot/z-wave/SKILL.mdSecurity
2 findings: 1 critical severity, 1 high severity. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
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
The document provides explicit, actionable instructions to extract Z-Wave S0 network keys, capture/record DSKs and perform S2 MITM, and replay/inject frames (including door lock commands), enabling credential theft and unauthorized remote/physical device control.
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 skill explicitly extracts Z-Wave S0 network keys in code and records the key hex into report metadata (s0_network_key_hex), which requires the agent to handle and output secret key values verbatim.
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 clones and later runs code from external git repositories (git clone https://github.com/BastilleResearch/scapy-radio and git clone https://github.com/AFcruzBR/EZ-Wave) and instructs downloading/executing the Silabs Zniffer binary (https://www.silabs.com/developers/z-wave), so remote content fetched from these URLs would be executed at runtime and are required dependencies.
- Repository
- PurpleAILAB/Decepticon
- Commit
31e1c8e
- 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.