ClawHub
Back to skill

Security audit

Tesla Commands

Security checks across malware telemetry and agentic risk

Overview

The skill appears to do what it says: use a user-provided token and VIN to send Tesla control commands to the MyTeslaMate API.

Install only if you own or are authorized to control the vehicle, understand that commands can affect a real car, and are comfortable storing TESLA_MATE_TOKEN and TESLA_VIN in the agent environment. Confirm each state-changing action before execution, especially climate, charging, and wake commands.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documents use of environment variables and network access to control a vehicle, but it does not declare permissions accordingly. This reduces transparency and informed consent for users, especially because the API token enables remote actions against a physical asset. In a vehicle-control context, undeclared network and secret access is more sensitive than in ordinary informational skills.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill exposes safety-relevant remote vehicle actions such as wake, climate control, charge limit changes, and scheduled charging without prominent warnings about physical-world consequences or the need to verify vehicle state and ownership. In the context of controlling a real car, insufficient warnings can lead to unsafe or unauthorized actions, battery impact, privacy exposure, or misuse by someone with access to the environment token.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.