Security audit

ble-device-control

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using a Bluetooth LE control tool, with some real device-control risks users should understand before using writes or background tasks.

Install only if you intend to let an agent operate local BLE devices through airctl. Verify the GitHub source before installing airctl, review commands before execution, be especially careful with writes or periodic write tasks because they can change device behavior, and stop any background tasks or daemon activity when finished.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The manifest description uses broad trigger terms like Bluetooth, BLE, scan, connect, read, write, and notify, plus imperative language such as MUST invoke. That can cause the skill to activate in many ordinary conversations involving BLE, increasing the chance an agent routes users into a capability that can enumerate, connect to, and modify nearby devices without sufficiently narrow intent matching.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The write workflow enables direct GATT writes after format validation but does not warn that writes can alter configuration, trigger actions, factory reset devices, or otherwise cause irreversible state changes. In BLE contexts, syntactically valid writes are not necessarily safe, so the omission of a safety gate makes unintended or harmful device modification more likely.

Static analysis

No suspicious patterns detected.