ClawHub
Back to skill

Security audit

Tesla Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is openly meant to control a Tesla, but it gives an agent sensitive vehicle-control authority without clear per-action confirmation rules.

Install only if you trust the teslacli/AgentGen source and are comfortable giving an agent Tesla account and vehicle-control authority. Inspect or pin the installer before running it, protect ~/.config/teslacli/, and require explicit approval for every command that unlocks, wakes, honks, changes climate, changes charging, or retrieves location/state data.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill explicitly enables remote vehicle control actions such as unlock, honk, flash, climate, and charging, but does not include meaningful safety, authorization, or consent checks before describing those capabilities. In context, this is more dangerous than ordinary device control because it affects a physical asset and could facilitate unauthorized access or unsafe actions if invoked for the wrong vehicle or user.

External Script Fetching

Low
Category
Supply Chain
Content
- teslacli
    install:
      - kind: shell
        cmd: "curl -fsSL https://raw.githubusercontent.com/Agent-Gen-com/tesla-cli/main/install.sh | sh"
        bins: [teslacli]
---
Confidence
97% confidence
Finding
The skill metadata installs software by piping a remotely fetched script directly into the shell. This creates a supply-chain and remote code execution risk because any compromise of the GitHub source, account, network path, or referenced branch would result in arbitrary code execution on the host during installation.

External Script Fetching

Low
Category
Supply Chain
Content
## Installation

```sh
curl -fsSL https://raw.githubusercontent.com/Agent-Gen-com/tesla-cli/main/install.sh | sh
```

Supports macOS (Intel & Apple Silicon) and Linux (x86_64 & ARM64).
Confidence
97% confidence
Finding
The installation instructions repeat the practice of fetching a remote script from GitHub and executing it immediately. Because this skill also handles highly sensitive Tesla OAuth tokens and private keys, compromise of the installer could steal credentials or implant malware with access to vehicle-control secrets.

Chaining Abuse

High
Category
Tool Misuse
Content
## Installation

```sh
curl -fsSL https://raw.githubusercontent.com/Agent-Gen-com/tesla-cli/main/install.sh | sh
```

Supports macOS (Intel & Apple Silicon) and Linux (x86_64 & ARM64).
Confidence
98% confidence
Finding
The use of `| sh` is a direct command-chaining pattern that executes untrusted network content without validation. In this skill's context, that is especially dangerous because the installed tool manages private keys, OAuth tokens, and remote vehicle control, so successful abuse could lead to host compromise and downstream unauthorized access to the user's Tesla account or vehicle.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.