v1.0.2

smart-control-skill

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 8:05 AM.

Analysis

The skill appears coherent, but it gives an AI agent authenticated control over smart-home devices and scenes without a clear confirmation boundary.

GuidanceReview this skill before installing because it can control real smart-home devices. Only configure it with a token you are comfortable granting device-control access to, keep that token private, and require explicit confirmation before turning devices on/off, changing AC settings, or triggering scenes.

Findings (3)

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.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Tool Misuse and Exploitation

SeverityHighConfidenceHighStatusConcern

SKILL.md

This skill provides AI agents with complete control over smart home devices ... air conditioner control, and scene automation

The skill explicitly grants agents control over physical smart-home devices and scene automation, but the provided artifacts do not require per-action user confirmation or narrow device/action scoping.

User impactA mistaken or autonomous invocation could turn devices on or off, change AC settings, or trigger a scene that changes multiple devices.

RecommendationUse only with explicit user-directed commands; add or require confirmation before any device mutation or scene trigger, and restrict the token or agent to specific devices where possible.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityMediumConfidenceHighStatusConcern

metadata

Required env vars: none ... Primary credential: none

This conflicts with the package artifacts that require MXCHIP_OAUTH_TOKEN for account-backed smart-home operations, so the registry metadata under-declares a sensitive permission boundary.

User impactUsers may not realize from the registry metadata that installing/configuring the skill involves granting an OAuth token capable of controlling their Smart Plus devices.

RecommendationDeclare MXCHIP_OAUTH_TOKEN as a required credential in registry metadata, document token scope clearly, and rotate or revoke the token if the skill is no longer needed.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceHighStatusNote

scripts/mxchip_mcp_client.py

base_url: str = "https://app.api.cloud.mxchip.com:2443/mcp" ... "Authorization": f"Bearer {self.oauth_token}" ... self.session.post(

The client sends the bearer token and device-control requests to the MXCHIP cloud MCP endpoint. This is purpose-aligned and disclosed, but users should understand the external data/control boundary.

User impactDevice names, IDs, actions, and the OAuth bearer token are used with the MXCHIP cloud service as part of normal operation.

RecommendationInstall only if you trust the MXCHIP endpoint and account flow; keep the token confidential and revoke it if device-control access should be removed.