ClawHub
Back to skill

Security audit

Arduino CLI

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Arduino CLI reference skill; it includes commands that can install Arduino components and upload firmware, but those actions are disclosed and aligned with its purpose.

Install this if you want Arduino CLI help. Before running upload commands, check the connected board, serial port, and FQBN with `arduino-cli board list`, because uploading firmware will modify the selected device.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest says the skill should be used when the user wants to "create, compile, or upload Arduino sketches" and triggers on phrases like "compile sketch". Phrases such as "compile sketch" are not specific to Arduino CLI and could overlap with general coding or embedded-development requests, increasing the risk of unintended invocation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill provides a direct firmware upload command to a connected device without warning that it will modify hardware state or advising the user to verify the target port and board before proceeding. In an agent context, this could lead to unintended overwriting of a connected board if a user follows the command blindly or if the skill is invoked with insufficient confirmation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.