CD kiwi-voice

Manage and configure Kiwi Voice assistant service. Use when starting/stopping Kiwi, editing voice config, checking logs, troubleshooting audio issues, or managing voice profiles.

ClawHub Agent Skills author: yuangu260 v1.0.0 MIT-0 80 files body ≈ 787 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 36/100 · Unfinished process — weak spots: steps, result and completion, when it triggers

Generator AI and agentstype 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

61/100

safety, quality, tests

Safety 60%: 51
Quality 40%: 77
Run on models: none yet

Process rating

36/100

Unfinished process

Steps w 15: 0
Result and completion w 14: 0
Inputs and preconditions w 11: 0

the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

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.

Broad scope 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 skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

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 · 41

✓ No critical or high findings

Medium and low: 41

medium Exfiltration net-redirectable-api-key kiwi/config_loader.py:422

Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
```
API key + configurable base URL from environment
```
medium Broad scope meta-agent-memory-dump SOUL.md

Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
```
SOUL.md
```
low Dangerous commands cmd-privilege config.yaml:237

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege config.yaml:241

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Exfiltration read-dotenv docs/deployment/local.md:16

Reads a .env file
```
cp .env.example .env              # Edit with your settings
```
low Dangerous commands cmd-background-process docs/deployment/systemd.md:31

Starts a background / autostarted process
```
sudo systemctl enable kiwi-voice
```
low Dangerous commands cmd-background-process docs/deployment/systemd.md:49

Starts a background / autostarted process (documentation table row)
```
| `systemctl enable kiwi-voice` | Enable on boot |
```
table
low Exfiltration exfil-webhook-url docs/features/voice-security.md:67

Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
```
2. Visit `https://api.telegram.org/bot<TOKEN>/getUpdates`
```
placeholder
low Exfiltration read-dotenv docs/getting-started/installation.md:57

Reads a .env file
```
cp .env.example .env
```
low Exfiltration read-dotenv docs/index.md:102

Reads a .env file
```
cp .env.example .env
```
low Dangerous commands cmd-privilege kiwi/locales/ar.yaml:317

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/ar.yaml:322

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/de.yaml:327

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/de.yaml:332

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/en.yaml:320

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/en.yaml:325

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/es.yaml:323

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/es.yaml:328

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/fr.yaml:328

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/fr.yaml:333

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/hi.yaml:317

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/hi.yaml:322

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/id.yaml:320

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/id.yaml:325

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/it.yaml:328

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/it.yaml:333

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/ja.yaml:312

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/ja.yaml:317

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/ko.yaml:311

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/ko.yaml:316

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/pl.yaml:323

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/pl.yaml:328

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/pt.yaml:326

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/pt.yaml:331

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/ru.yaml:345

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/ru.yaml:349

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/tr.yaml:318

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/tr.yaml:323

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Dangerous commands cmd-privilege kiwi/locales/zh.yaml:292

Privilege escalation / world-writable permissions (string literal in code, not executed)
```
- "sudo rm -rf"
```
code literal
low Dangerous commands cmd-privilege kiwi/locales/zh.yaml:297

Privilege escalation / world-writable permissions (negated — the text forbids it)
```
- "chmod 777"
```
negated
low Exfiltration read-dotenv README.md:88

Reads a .env file
```
cp .env.example .env
```

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

✓ No remarks against the Agent Skills spec

Process rating: all ten parameters 36/100

0Steps. Prose only: no discrete steps
0Result and completion. Does not say what the result is
0Inputs and preconditions. Does not say what the process needs to start
20When it triggers. No condition that starts the skill
30Running it twice. 3 mutating operations with no state check
55Failures and branches. 1 branches
60Tools and files. Uses tools (bash, python) that frontmatter does not declare
100Consistency. Name and required fields are in place
100Execution cost. Instruction body is 787 tokens
100Progress reporting. Reports progress

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

+5Description has no quoted example phrases that should trigger the skill
+4Description does not say when NOT to use the skill (false activations)
+3No numbered steps or checklist
+3Output format is not stated: the model decides each time
-41 reference files, but SKILL.md never points to them: the model will not open them
+1No license
+2Single-language instructions
+3Description length 178: enough signal without eating the budget
+4Structure: 12 headings
+4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious

The skill is a real Kiwi Voice service, but it grants and encourages broad voice-driven agent control beyond its narrow management description.

LLM: suspicious (high) · VirusTotal: · 29 May 2026

Tests

— no evals.json

— no spec.yaml

— not run on models

Files · 80

CLAUDE.md 9K
config.yaml 10K
custom_components/kiwi_voice/button.py 4K
custom_components/kiwi_voice/config_flow.py 4K
custom_components/kiwi_voice/const.py 0K
custom_components/kiwi_voice/coordinator.py 6K
custom_components/kiwi_voice/manifest.json 0K
custom_components/kiwi_voice/sensor.py 6K
custom_components/kiwi_voice/services.yaml 1K
custom_components/kiwi_voice/strings.json 1K
custom_components/kiwi_voice/switch.py 3K
custom_components/kiwi_voice/translations/en.json 1K
custom_components/kiwi_voice/tts.py 3K
custom_components/kiwi_voice/__init__.py 6K
docs/api/rest.md 4K
docs/api/websocket.md 3K
docs/deployment/docker.md 2K
docs/deployment/gpu.md 2K
docs/deployment/local.md 2K
docs/deployment/reverse-proxy.md 1K
docs/deployment/systemd.md 1K
docs/development/architecture.md 3K
docs/development/code-patterns.md 2K
docs/development/contributing.md 3K
docs/features/home-assistant.md 2K
docs/features/multilanguage.md 3K
docs/features/souls.md 2K
docs/features/speaker-id.md 2K
docs/features/streaming-tts.md 2K
docs/features/stt-engines.md 3K
docs/features/tts-providers.md 3K
docs/features/voice-security.md 3K
docs/features/wake-word.md 3K
docs/features/web-dashboard.md 2K
docs/features/web-microphone.md 2K
docs/getting-started/configuration.md 4K
docs/getting-started/first-run.md 2K
docs/getting-started/installation.md 2K
docs/index.md 5K
kiwi/api/audio_bridge.py 9K
kiwi/api/server.py 40K
kiwi/api/__init__.py 0K
kiwi/config_loader.py 34K
kiwi/event_bus.py 14K
kiwi/hardware_aec.py 16K
kiwi/i18n.py 2K
kiwi/integrations/homeassistant.py 9K
kiwi/integrations/__init__.py 0K
kiwi/listener.py 123K
kiwi/locales/ar.yaml 17K
kiwi/locales/de.yaml 16K
kiwi/locales/en.yaml 15K
kiwi/locales/es.yaml 15K
kiwi/locales/fr.yaml 16K
kiwi/locales/hi.yaml 24K
kiwi/locales/id.yaml 15K
kiwi/locales/it.yaml 15K
kiwi/locales/ja.yaml 17K
kiwi/locales/ko.yaml 15K
kiwi/locales/pl.yaml 15K

Dates

In catalog since 18 Mar 2026

Updated in catalog 18 May 2026

First seen here 10 Sept 2026

Last analysis 11 Sept 2026, 02:30 UTC

Last seen in crawl 9 h ago

Score history

Date		Score	Safety	Qual.
10 Sept 2026	C	61	51	77