ClawHub
Back to skill

Security audit

Bambu Lab Local Control

Security checks across malware telemetry and agentic risk

Overview

This skill is a real local 3D-printer control tool, but it gives an agent broad hardware control without safety guardrails and weakens MQTT TLS verification.

Install only if you are comfortable letting an agent directly control your 3D printer. Keep config.json private, use it only on a trusted local network, and require explicit human confirmation before any non-status command, especially stop, temperature changes, or raw G-code.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

High
Confidence
95% confidence
Finding
The skill exposes a generic `gcode` subcommand that forwards arbitrary raw G-code directly to the printer, which materially expands capability beyond ordinary printer control operations like status, pause, resume, light, and speed control. Raw G-code can alter temperatures, move axes, disable safeties, or otherwise perform destructive actions, making this a dangerous hidden capability in the context of a general local-control skill.

Context-Inappropriate Capability

High
Confidence
97% confidence
Finding
`send_gcode()` accepts unvalidated user input and publishes it as a `gcode_line` command to the printer. In a 3D-printer control context, arbitrary G-code is effectively direct device instruction execution and can be used to overheat components, crash motion systems, interrupt prints, or damage hardware and surroundings.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation exposes commands that can directly alter printer behavior, including stop/resume, temperature changes, speed changes, lighting, and arbitrary G-code execution, without warning users about safety, equipment, or print-integrity risks. In a local hardware-control skill, these actions can damage prints, stress hardware, create thermal hazards, or cause unintended motion if invoked carelessly or through an agent without explicit confirmation.

Missing User Warnings

High
Confidence
96% confidence
Finding
The skill exposes arbitrary G-code execution without any warning, confirmation, or safety disclosure, despite the fact that such commands can directly control heaters and motion systems. In this context, the lack of user-facing warning makes accidental or abusive dangerous operations substantially more likely.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.