小米智能家居 (Xiao Mi Home for HA)

Security checks across static analysis, malware telemetry, and agentic risk

Overview

The skill matches its smart-home purpose, but it gives the agent broad Home Assistant control through a long-lived token without clear service/entity limits or confirmation safeguards.

Install only if you are comfortable giving the agent persistent Home Assistant access. Use a restricted HA account/token if possible, avoid broad automations unless needed, and require confirmation before the agent changes device states or triggers scenes.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

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.

#
ASI02: Tool Misuse and Exploitation
High
What this means

If invoked incorrectly, the agent could turn devices on or off, change climate settings, trigger scenes, or run automations in the user's home.

Why it was flagged

The skill exposes broad Home Assistant service-calling authority rather than limiting actions to a defined set of safe Xiaomi entities or services.

Skill content
调用任意 HA 服务(脚本、场景、自动化)/ Call any HA service (scripts, scenes, automations)
Recommendation

Limit the token and skill to specific entities/services where possible, and require explicit user confirmation before any state-changing Home Assistant POST request.

#
ASI03: Identity and Privilege Abuse
High
What this means

A long-lived HA token stored for the skill could allow broad smart-home control across sessions if misused or exposed.

Why it was flagged

The skill requires a persistent Home Assistant token, which can carry broad account/device privileges; this sensitive credential requirement is not reflected in the supplied registry metadata.

Skill content
`HA_TOKEN` | 长期访问令牌 (Long-Lived Access Token) | ✅ 必填
Recommendation

Use the least-privileged Home Assistant account/token available, rotate the token if no longer needed, and avoid sharing it in chat logs or other visible channels.

#
ASI08: Cascading Failures
Medium
What this means

One mistaken command could propagate through Home Assistant automations and change several devices or household routines at once.

Why it was flagged

Scenes, scripts, and automations can affect multiple devices or routines from a single service call, and the artifacts do not document containment or rollback safeguards.

Skill content
Call any HA service (scripts, scenes, automations)
Recommendation

Keep automations/scripts out of scope unless explicitly requested, and add confirmation for actions that trigger scenes, scripts, or multi-device automations.

#
ASI04: Agentic Supply Chain Vulnerabilities
Low
What this means

Installing global packages can introduce third-party code onto the user's machine.

Why it was flagged

The optional fallback installs an unpinned global npm package; this is disclosed and user-directed, but it adds ordinary dependency-provenance risk.

Skill content
npm i -g node-jq   # 安装后 jq 命令即可用
Recommendation

Prefer the OS package manager for jq, or pin and verify any npm package before installing it globally.