iot-overview
Use when the engagement target is IoT, embedded Linux, RTOS, or any device reachable via UART/JTAG/SWD or by extracting its firmware. Covers firmware acquisition, binwalk extraction, filesystem mounting, default-credential hunting, bootloader attacks, wireless protocol sidebands (BLE, Zigbee, Z-Wave, LoRaWAN, sub-GHz).
66
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
3 findings: 1 critical severity, 1 high severity, 1 medium 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
This repository is an offensive IoT/embedded attack playbook containing explicit instructions for credential theft, data exfiltration, remote code execution, persistent backdoors, RF jamming/replay and rogue gateway/device control—i.e., deliberate malicious techniques and backdoor creation.
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 files for literal, high-entropy values that could be used as secret keys. I flagged values that are explicit byte/hex keys in the documentation and look usable (not simple placeholders or low-entropy defaults). - zigbee-touchlink/SKILL.md:61-65 — The document prints the ZLL Master Key as a 16-byte hex string ("9F 55 95 ... 0D"). This is a real transport key (well-known in the ZigBee/ZLL spec) and is a high-entropy literal that can be used to derive per-device transport keys; therefore it meets the definition of a secret in this context. - lorawan-otaa/SKILL.md:119 — The LoRaWAN example contains an APP_KEY literal ("2B7E151628AED2A6ABF7158809CF4F3C") used as a known/extracted AES key in example code. This is a 16-byte AES key presented as a concrete value and is a usable high-entropy secret in the example. Ignored potential/non-actionable values: - Repeated illustrative hex patterns like "AABBCCDDEEFF0011" (used as placeholders/dev_eui/manufacturer-key examples) — these are clearly example placeholders and/or low-entropy patterned values, so I did not flag them. - DEFAULT_KEY = b'\x00' * 16 (zero key) and similar all-zero/default values are low-entropy defaults and intentionally documented; not flagged. - IP addresses, example payloads, and other demonstration strings (e.g., "00AABB...") are examples for illustration and not flagged. - No PEM/private-key blocks or API tokens were present beyond the keys noted above.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The catalog explicitly includes actions that access/modify low-level host resources ("/dev/mem, /dev/kmem, MTD writes"), mounting filesystems and inspecting/modifying /etc/passwd, which imply using root privileges and can change the machine state.
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
Multiple skills include git clone + build/install commands that fetch remote repositories and execute their build/install scripts at setup time (e.g., https://github.com/devttys0/sasquatch, https://github.com/IOActive/laf, https://github.com/rpp0/gr-lora, https://github.com/brocaar/chirpstack-docker, https://github.com/BastilleResearch/scapy-radio, https://github.com/AFcruzBR/EZ-Wave, https://github.com/riverloopsec/killerbee, https://github.com/ulissesdias/keeloq_tools), which are runtime external dependencies that pull and run remote code and are listed as required prerequisites.
- Repository
- PurpleAILAB/Decepticon
- Commit
0cf691e
- 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.