SKILLEMALL.ai
GitHub ↗ RU Sign in

BF voice-agent-pro-v3

Gives any OpenClaw agent a complete voice layer via ElevenLabs. Clones the principal's voice from audio samples, converts any text to MP3 audio (VSL, podcasts, video narrations, nurturing sequences), and deploys a conversational AI agent for automated inbound and outbound calls via Twilio. Use when the agent needs to generate audio content, call leads, or answer prospects 24/7 in the principal's cloned voice. Requires ELEVENLABS_API_KEY and ELEVENLABS_VOICE_ID — see Setup section in SKILL.md.

ClawHub Agent Skills author: Wesley Armando v1.0.7 MIT-0 7 files body ≈ 4 141 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 21/100 · Will not run — References files that are not bundled: references/setup_guide.md

GeneratorTelegramAI 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
B
84/100
safety, quality, tests
Safety 60%
90
Quality 40%
76
Run on models
none yet
Process rating
F
21/100
Will not run
References files that are not bundled: references/setup_guide.md
Tools and files w 18
0
Steps w 15
0
Result and completion w 14
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.

How to improve

  1. The text references files that are not there: add them or drop the references.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-credential-use setup_guide.md:236
    Credential used in a network call (verify the destination is the intended service)
    → Delete: curl -X DELETE .../v1/voices/$VOICE_ID -H "xi-api-key: $KEY"
  • medium Exfiltration net-credential-use setup_guide.md:240
    Credential used in a network call (verify the destination is the intended service)
    → curl -s .../v1/voices -H "xi-api-key: $KEY" | python3 -m json.tool

Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/setup_guide.md

Process rating: all ten parameters 21/100

Will not run. References files that are not bundled: references/setup_guide.md
  • 0Tools and files. 1 referenced file(s) missing: references/setup_guide.md
  • 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
  • 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
  • 40Consistency. Frontmatter name (voice-agent-pro-v3) differs from the folder (voice-agent-pro-v1)
  • 70Execution cost. Instruction body is 4141 tokens
  • 100Failures and branches. 2 branches, has a failure section
  • low 10 top-level sections: this looks like several domains in one skill

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
  • +2Single-language instructions
  • +3Description length 497: enough signal without eating the budget
  • +4Structure: 33 headings
  • +4Has examples (28 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This is an openly described voice-cloning and calling skill, but it needs Review because it can automate calls in a cloned voice while under-specifying consent, disclosure, credential handling, and data retention.
LLM: suspicious (high) · VirusTotal: · 29 May 2026