Bambu Lab

• Outcome: Review
• Latest audit: May 28, 2026, 9:37 AM
• Version:
  0.1.0

Overview

This printer-control skill is mostly purpose-aligned, but it ships with hardcoded printer credentials and under-disclosed security risks that users should review before installing.

Install only after replacing the bundled host, serial number, and access code with your own secure configuration. Treat the serial and access code as printer credentials, rotate them if they were ever real, and be aware that commands can pause, stop, or otherwise alter a physical print job while monitoring can keep running and store printer status locally.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (8)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 80% confidence
• Finding: The skill documentation describes capabilities that imply network access, file I/O, and likely environment-variable usage, but no permissions are declared. This creates a transparency and policy-enforcement gap: users and platforms cannot accurately assess or restrict what the skill may access before use.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 88% confidence
• Finding: The documented behavior exceeds the declared purpose by including additional control and integration functions such as resume, light control, fan control, raw MQTT output, and notification/file-writing behaviors. This mismatch undermines informed consent and increases the chance that users enable broader device control or data handling than they expected.

Context-Inappropriate Capability

Medium

• Confidence: 98% confidence
• Finding: The documentation contains a concrete serial number and access code, which are credential-like secrets for controlling a LAN-connected printer. Publishing such values can enable unauthorized access to the device if they are real, and even if they are placeholders, they normalize unsafe secret-handling practices.

Context-Inappropriate Capability

Medium

• Confidence: 89% confidence
• Finding: The fan-control implementation sends a raw G-code line via the generic `gcode_line` command rather than using a narrower, purpose-built API. Even though the current parameter is locally constructed as `M106 S<pwm>`, exposing generic G-code transport broadens the control mechanism and can normalize a pattern that could be extended to unsafe printer actions, especially in an automation context controlling physical hardware.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The documented commands include disruptive and persistent actions such as stopping prints and running background monitoring, but the documentation does not warn about operational impact. In the context of a physical device, unexpected stop/pause/background actions can waste material, interrupt jobs, or leave persistent monitoring processes running without user awareness.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill description exposes credential-like configuration values without any warning that they are sensitive authentication data. In a networked device-control skill, this is especially dangerous because those values may allow direct MQTT access to a physical printer on the local network.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The script publishes operational MQTT commands directly to the printer, allowing state-changing actions such as pause, resume, stop, and light control with minimal user friction. In a device-control skill, missing explicit warnings and guardrails can lead to unintended disruption of an active print job or unsafe remote manipulation, especially because the same script also embeds credentials and can immediately act on a reachable printer.

Missing User Warnings

High

• Confidence: 99% confidence
• Finding: The script embeds a default host, serial number, and access code directly in source, which exposes live device credentials to anyone who can read the file or logs derived from it. For a LAN-mode printer, these values can enable unauthorized monitoring and control, including pausing or stopping prints and modifying printer state without the owner's consent.

VirusTotal

66/66 vendors flagged this skill as clean.