SKILLEMALL.ai
GitHub ↗ RU Sign in

CC universal-voice-agent

Real-time goal-oriented voice calling agent. Use when you need to make phone calls with a specific objective: place orders, make reservations, customer service, encouragement calls, or any conversational goal. Haiku runs the call in real-time with your voice (ElevenLabs), transcribes responses (Groq Whisper), adapts intelligently to conversation flow, handles silence/holds, and sends you an SMS summary. No scripts, pure real-time reasoning.

Not recommendedcritical or high security findings
modbender/skill-library-mcp Agent Skills author: modbender MIT 10 files · 1 script body ≈ 1 042 tokens Open the sourcegithub.com↗ analyzed 3 d ago

Real-time goal-oriented voice calling agent.

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

GeneratorAI 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
64/100
safety, quality, tests
Safety 60%
57
Quality 40%
75
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

The same skill appears in 2 more places: skill-library-mcp, skill-library-mcp

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.

Exfiltration
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.
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 · 14

  • high Exfiltration exfil-webhook-url references/WEBSOCKET_SETUP.md:66
    Webhook / callback URL commonly used for exfiltration (verify the destination)
    Forwarding                    https://abc1….io -> http://loca…000
Medium and low: 13
  • medium Exfiltration exfil-webhook-url README.md:27
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    Set **Webhook URL** to: `https://abc1….io/call-webhook`
    quoted
  • medium Exfiltration exfil-webhook-url references/WEBSOCKET_SETUP.md:74
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    - **Webhook URL**: `https://abc1….io/call-webhook`
    quoted
  • medium Exfiltration exfil-webhook-url SETUP.md:85
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    3. Set URL to: `https://abc1….io/call-webhook`
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:22
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…GLi+2W/6ao+6Y7gu/RCwR…Kng==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:44
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Jqj+nOOr…S5A==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:72
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…9dM/mwVgvbZJaSNaRk+bshk…Kbz+IoId…W0Q==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:78
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…Zif+qXa4n+oYzK…TZQ/vlgJrCoNQlg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:157
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…SDq+2kAA…MOe/+5cdoEdg==",
    detector
  • low Exfiltration exfil-webhook-url README.md:21
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    Copy the ngrok URL (e.g., `https://abc1….io`)
    demoquoted
  • low Secrets in code secret-high-entropy-token run.sh:4
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    export TWILIO_ACCOUNT_SID="AC35…ca9"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/agent.js:21
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const TWILIO_ACCOUNT_SID = process.env.TWILIO_ACCOUNT_SID || 'AC35…ca9';
    quoted
  • low Secrets in code secret-high-entropy-token scripts/websocket-server.js:29
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    const ACCOUNT_SID = process.env.TWILIO_ACCOUNT_SID || 'AC35…ca9';
    quoted
  • low Exfiltration exfil-webhook-url SETUP.md:78
    Webhook / callback URL commonly used for exfiltration (verify the destination) (security demo / example; quoted — discussed, not commanded)
    Copy the ngrok URL (e.g., `https://abc1….io`)
    demoquoted

Files scanned: 10. 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: Real-time goal-oriented voice calling agent. Use when you need to … ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value

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. 3 mutating operations with no state check
  • 100Tools and files. No external tools needed
  • 100Steps. 39 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1042 tokens

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
  • -31 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 444: enough signal without eating the budget
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (1 of 2)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.