SKILLEMALL.ai
GitHub ↗ RU Sign in

DC openclaw-xiaomi-home

Your OpenClaw can now control your smart home. It connects to your Xiaomi/Mijia devices through Home Assistant and lets you control lights, AC, locks, sensors and more with plain text or voice commands. Ask things like "turn on the living room light", "set AC to 26 degrees", "is the front door locked?", or "what's the bedroom temperature?" and your AI assistant handles it instantly. Triggers: "turn on the light", "set AC temperature", "is the door locked?", "check the temperature", "lock the door", "turn everything off".

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: canmaxfire v1.2.2 MIT-0 14 files · 1 script body ≈ 533 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
D
52/100
safety, quality, tests
Safety 60%
48
Quality 40%
58
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 10

  • high Dangerous commands cmd-persistence README.md:96
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load ~/.openclaw/skills/openclaw-xiaomi-home/scripts/ha-mcp-server/ai.openclaw.ha-mcp.plist
  • high Dangerous commands cmd-persistence scripts/setup.sh:86
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    launchctl load "$PLIST_DST" 2>/dev/null || true
Medium and low: 8
  • medium Exfiltration net-credential-use references/api-notes.md:29
    Credential used in a network call (verify the destination is the intended service)
    curl -H "Authorization: Bearer $HA_TOKEN" \
  • medium Dangerous commands cmd-persistence scripts/setup.sh:84
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    PLIST_DST="$HOME/Library/LaunchAgents/ai.openclaw.ha-mcp.plist"
    code literal
  • low Exfiltration read-dotenv README.md:89
    Reads a .env file
    npm install && cp .env.example .env
  • low Secrets in code secret-high-entropy-token scripts/ha-mcp-server/package-lock.json:227
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…l1I+R1H7…G3i/cYFJ…fIw==",
    detector
  • low Secrets in code secret-high-entropy-token scripts/ha-mcp-server/package-lock.json:261
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…XcW+/GvMN…kxZ/opySAZMrc+9LY/WyjA…InQ==",
    detector
  • low Secrets in code secret-high-entropy-token scripts/ha-mcp-server/package-lock.json:278
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…qEP+UeRV…fdw==",
    detector
  • low Secrets in code secret-high-entropy-token scripts/ha-mcp-server/package-lock.json:312
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Fnw/+3lVx…cQS+Yu6w==",
    detector
  • low Secrets in code secret-high-entropy-token scripts/ha-mcp-server/package-lock.json:414
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…UzV+AA46…P4O+ng17CA==",
    detector

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning frontmatter-yaml SKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Your OpenClaw can now control your smart home. It connects to your… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "NOTE"
  • note frontmatter-key unknown frontmatter key "Security"

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 4 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 533 tokens
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -44 reference files, but SKILL.md never points to them: the model will not open them
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 10 example trigger phrases
  • +3Description length 526: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 4 items
  • +4Has examples (4 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: suspicious
The skill matches its smart-home purpose, but it gives broad AI-driven control over locks and other physical devices while under-disclosing credential, network, and persistence risks.
LLM: suspicious (high) · VirusTotal: · 29 May 2026