lorawan-otaa
LoRaWAN OTAA join-procedure analysis (DevEUI/AppEUI/AppKey extraction), frame-counter replay on ABP devices, downlink injection via rogue gateway, bit-flipping on unprotected FRMPayload, and network enumeration with ChirpStack and the LoRaWAN Auditing Framework.
77%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Fix and improve this skill with Tessl
tessl review fix ./packages/decepticon/decepticon/skills/standard/iot/lorawan-otaa/SKILL.mdE006: 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 provides explicit, actionable offensive instructions for extracting LoRaWAN keys from firmware, exfiltrating credentials, replaying uplinks, and operating a rogue gateway to inject downlinks (including OTA), enabling remote compromise of devices and networks.
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 instructs extracting AppKey/AppSKey values from firmware and embedding them (and a JWT token) into commands, code, and findings (e.g., kg_add_node), which requires the LLM to handle and output secret values verbatim — a direct secret-exfiltration risk.
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 skill explicitly instructs running a command with sudo ("sudo make install"), which requests elevated privileges and can modify system-wide files, so it pushes the agent to compromise the machine state.
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 includes git clone and install commands that fetch and build/execute remote code at runtime (e.g., https://github.com/IOActive/laf, https://github.com/rpp0/gr-lora, https://github.com/brocaar/chirpstack-docker), making those repositories required runtime dependencies that execute external code.
- 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.