Trust Assessment
meshtastic received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 11 findings: 3 critical, 3 high, 4 medium, and 1 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, Unsafe deserialization / dynamic eval.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 3/100, indicating areas for improvement.
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 Findings11
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions systemd service persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/lukevr/meshtastic-skill/scripts/mesh.py:217 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/lukevr/meshtastic-skill/scripts/mesh.py:163 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/lukevr/meshtastic-skill/scripts/mesh.py:209 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'cmd_setup'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/lukevr/meshtastic-skill/scripts/mesh.py:163 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'cmd_setup'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/lukevr/meshtastic-skill/scripts/mesh.py:209 | |
| HIGH | Prompt Injection via Untrusted Log File The `mqtt_bridge.py` script writes messages received from the global Meshtastic MQTT network (an untrusted external source) directly to `/tmp/mesh_messages.txt`. The `SKILL.md` documentation explicitly instructs the LLM agent to read and process this file as part of its prompt context (e.g., 'Check /tmp/mesh_messages.txt for new messages...'). A malicious actor on the Meshtastic network could craft messages containing prompt injection instructions, which the LLM agent might then execute, potentially leading to unauthorized actions, data exfiltration, or manipulation of the agent's behavior. Implement robust sanitization or a dedicated parsing layer for content from `/tmp/mesh_messages.txt` before it is included in an LLM's prompt. Do not directly inject raw untrusted content into the LLM's context. Consider using a tool that extracts specific fields from the messages file and passes only those fields as structured data to the LLM, rather than the raw text. | LLM | scripts/mqtt_bridge.py:200 | |
| 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/lukevr/meshtastic-skill/scripts/mesh.py:4 | |
| 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/lukevr/meshtastic-skill/scripts/mcp_server.py:19 | |
| 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/lukevr/meshtastic-skill/scripts/mesh.py:10 | |
| 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/lukevr/meshtastic-skill/scripts/mqtt_bridge.py:18 | |
| LOW | Hardcoded Public MQTT Credentials The `mqtt_bridge.py` script contains hardcoded username and password (`meshdev`, `large4cats`) for connecting to public Meshtastic MQTT brokers (`mqtt.meshtastic.org` and `mqtt.meshtastic.es`). While these appear to be public test credentials for the Meshtastic network, hardcoding any credentials, even public ones, is generally not a best practice. If these were ever intended to be private or if the public credentials were compromised, it could pose a risk. Store credentials securely, preferably using environment variables, a secrets management system, or a configuration file that is not committed to version control. For public credentials, explicitly document their public nature and consider if they are truly necessary to be hardcoded or if anonymous access is sufficient. | LLM | scripts/mqtt_bridge.py:40 |
Scan History
Embed Code
[](https://skillshield.io/report/9c578cfe2c8d9f01)
Powered by SkillShield