SKILLEMALL.ai
RU Sign in

CC clack

Deploy and manage Clack, a voice relay server for OpenClaw. Bridges voice input (WebSocket) through STT → OpenClaw agent → TTS, enabling real-time voice conversations with your agent. Supports ElevenLabs, OpenAI, and Deepgram for STT/TTS. Per-session provider selection — users can independently choose STT and TTS providers (including on-device) from the app settings. Encrypted connections via Domain (SSL) or Tailscale. Supports local speech mode where STT/TTS run on-device and only LLM calls go through the server. Use when a user wants to set up voice chat, voice relay, voice interface, Clack, or talk to their agent by voice.

ClawHub Agent Skills author: fbn3799 v1.5.3 10 files · 4 scripts body ≈ 3 771 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

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

ProcedureAI 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
C
72/100
safety, quality, tests
Safety 60%
70
Quality 40%
74
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Failures and branches w 10
0
Progress reporting w 2
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.

Dangerous commands 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 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

    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

    ✓ No critical or high findings

    Medium and low: 10
    • medium Dangerous commands cmd-pipe-to-shell CHANGELOG.md:6
      Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
      - **Tailscale APT install**: Replaced `curl | sh` with official APT repository for Tailscale installation
      quoted
    • medium Dangerous commands cmd-privilege README.md:46
      Privilege escalation / world-writable permissions
      sudo bash ~/.openclaw/skills/clack/scripts/setup.sh
    • medium Exfiltration net-credential-use scripts/pair.sh:29
      Credential used in a network call (verify the destination is the intended service)
      RESPONSE=$(curl -s "http://localhost:${PORT}/pair?token=…")
    • medium Exfiltration net-credential-use scripts/setup.sh:415
      Credential used in a network call (verify the destination is the intended service)
      PAIR_RESPONSE=$(curl -s "http://localhost:${PORT}/pair?token=…" 2>/dev/null || true)
    • medium Dangerous commands cmd-privilege SKILL.md:42
      Privilege escalation / world-writable permissions
      sudo bash scripts/setup.sh
    • low Exfiltration exfil-secret-in-url scripts/pair.sh:29
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      RESPONSE=$(curl -s "http://localhost:${PORT}/pair?token=…")
      placeholder
    • low Dangerous commands cmd-privilege scripts/setup.sh:3
      Privilege escalation / world-writable permissions (code comment; security demo / example)
      # Usage: sudo bash scripts/setup.sh [--port 9878] [--domain clack.example.com]
      commentdemo
    • low Dangerous commands cmd-privilege scripts/setup.sh:7
      Privilege escalation / world-writable permissions (string literal in code, not executed)
      echo "Please run with sudo: sudo bash $0 $*"
      code literal
    • low Dangerous commands cmd-background-process scripts/setup.sh:386
      Starts a background / autostarted process
      systemctl enable clack
    • low Exfiltration exfil-secret-in-url scripts/setup.sh:415
      Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
      PAIR_RESPONSE=$(curl -s "http://localhost:${PORT}/pair?token=…" 2>/dev/null || true)
      placeholder

    Files scanned: 10. 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 51/100

    • 0Result and completion. Does not say what the result is
    • 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. 18 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 60 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3771 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 16 top-level sections: this looks like several domains in one skill
    • low The response is described with custom markup (5 tags): a typed call is more reliable

    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)
    • +3Output format is not stated: the model decides each time
    • -5TODO / placeholder text left in the skill
    • -2localhost URLs: will not work for another user
    • -34 of 5 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 633: enough signal without eating the budget
    • +4Structure: 33 headings
    • +3Step-by-step instructions: 60 items
    • +4Has examples (8 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.

    External checks

    ClawHub: suspicious
    Clack appears to be a real voice relay skill, but it should go to Review because it stores sensitive voice context and tokens while its pairing and auth controls are weaker than the documentation suggests.
    LLM: suspicious (high) · VirusTotal: benign · 28 May 2026