Tesla Commands

ReviewAudited by ClawScan on May 10, 2026.

Overview

The skill matches its Tesla-control purpose, but it gives an agent token-backed ability to change vehicle settings and schedules, including an undocumented schedule-removal command, without clear approval safeguards.

Install only if you want the agent to control Tesla vehicle functions through MyTeslaMate. Before use, confirm the exact VIN and action, avoid leaving the API token available longer than necessary, and be especially careful with charging schedule changes or removals.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Medium

#ASI02: Tool Misuse and Exploitation

What this means

If invoked incorrectly, the agent could change climate or charging settings on a real vehicle, potentially affecting battery use, charging behavior, cost, or user expectations.

Why it was flagged

The tool sends POST commands that change live vehicle state, but the artifacts do not show confirmation prompts, safety gating, or enforcement of the documented charge-limit range before sending the request.

Skill content

elif args.climate:
        action = "auto_conditioning_start" if args.climate == "on" else "auto_conditioning_stop"
        print(json.dumps(call_api(f"command/{action}", method="POST", vin=args.vin)))
    elif args.charge_limit:
        print(json.dumps(call_api("command/set_charge_limit", method="POST", data={"percent": args.charge_limit}, vin=args.vin)))

Recommendation

Require explicit user confirmation for every mutating vehicle command, validate local input ranges, and make the target VIN and requested action clear before execution.

Medium

#ASI09: Human-Agent Trust Exploitation

What this means

A user may install the skill expecting only the documented actions, while the executable includes an additional schedule-deletion action.

Why it was flagged

The code exposes a command that completely removes charge schedules, but SKILL.md lists only set and clear schedule options and does not document this more destructive capability.

Skill content

parser.add_argument("--remove-schedules", action="store_true", help="Completely remove all charge schedules")
...
elif args.remove_schedules:
        # According to Tesla Fleet API, remove_charge_schedule completely deletes the configuration
        print(json.dumps(call_api("command/remove_charge_schedule", method="POST", data={}, vin=args.vin)))

Recommendation

Document all mutating commands in SKILL.md, especially destructive or irreversible ones, and require confirmation before removing schedules.

Medium

#ASI03: Identity and Privilege Abuse

What this means

Anyone or any agent session with this token available can access the configured MyTeslaMate account functions exposed by the tool.

Why it was flagged

The skill requires a bearer token for vehicle access, but the supplied registry metadata declares no required environment variables and no primary credential, reducing visibility into the privilege being granted.

Skill content

- `TESLA_MATE_TOKEN`: Your MyTeslaMate API token.
- `TESLA_VIN`: Your vehicle's VIN

Recommendation

Declare the token and VIN requirements in metadata, use the least-privileged API token available, and avoid exposing the token outside sessions where vehicle control is needed.

Low

#ASI06: Memory and Context Poisoning

What this means

Using the status command may reveal private vehicle telemetry, including location, to the agent context.

Why it was flagged

Vehicle status output can include sensitive location and lock-state information that may enter the agent conversation or logs.

Skill content

- `--status`: Fetch full vehicle data (battery, climate, location, locks, etc.).

Recommendation

Use status queries only when needed, avoid sharing outputs unnecessarily, and treat vehicle location and lock status as sensitive information.