Trust Assessment
snapmaker received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, Suspicious import: socket, Arbitrary G-code Command Injection via Moonraker API.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Arbitrary G-code Command Injection via Moonraker API The skill allows arbitrary G-code commands to be sent to the Snapmaker printer via the `scripts/snapmaker.py gcode <CMD>` command. The `<CMD>` argument, which is untrusted input from the LLM, is directly interpolated into the Moonraker API request path (e.g., `/printer/gcode/script?script=<CMD>`). An attacker could exploit this to send malicious G-code, potentially causing physical damage to the printer, initiating dangerous movements, or triggering firmware-level actions that could lead to data exfiltration or further compromise if the printer's underlying system allows it (e.g., via custom G-code macros that execute shell commands). This grants excessive control over the physical device. Implement a strict whitelist of allowed G-code commands or command patterns. If arbitrary G-code is deemed necessary, ensure robust sanitization and validation of the input `<CMD>` to prevent dangerous or unintended operations. Consider adding a confirmation step for potentially destructive commands before execution. | LLM | scripts/snapmaker.py:71 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/lucakaufmann/snapmaker/scripts/snapmaker.py:17 | |
| MEDIUM | Suspicious import: socket Import of 'socket' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/lucakaufmann/snapmaker/scripts/snapmaker.py:22 |
Scan History
Embed Code
[](https://skillshield.io/report/8d8fe2468924c4cf)
Powered by SkillShield