SKILLEMALL.ai
GitHub ↗ RU Sign in

CC paired

Paired: Phone Agent. Bridges an OpenClaw agent to the user's own phone via Bluetooth and ADB. Provides SMS receive (MAP/MNS), SMS send (ADB), outgoing/incoming calls (HFP), contacts (PBAP), media control (AVRCP), file transfer (OBEX), PAN tethering, and v2.0.0+ voice cloning so the agent speaks in the user's own voice with word-level audio splicing and 30-language multilingual synthesis. Zero recurring cost, no Twilio, Telnyx, Vapi, ElevenLabs, or rented numbers. Voice cloning runs locally via VoxCPM2 (primary, 48kHz studio) with XTTS v2 fallback (24kHz), piper fallback (generic), and espeak-ng last resort. Triggers on phrases like "send SMS", "text someone", "call my phone", "make a call", "what's on my phone", "my contacts", "phone contacts", "play music", "pause", "next track", "send file to phone", "tether", "paired devices", "is my phone connected", "say it in my voice", "voice note", "speak as me", "clone my voice", "Bluetooth", "BT", "/sms", "/phone", "/voice", "/say", "ofono", "AVRCP", "MAP". Configuration lives in ~/.config/paired/paired.conf (phone MAC, adapter, trusted numbers list) and ~/.config/paired/voice.conf (voice cloning config, only if voice features are enabled). Always read the config before acting; never hardcode phone identifiers.

ClawHub Agent Skills author: Only 1 Naren v2.0.0 MIT-0 65 files · 2 scripts body ≈ 4 262 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process C 63/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

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
60/100
safety, quality, tests
Safety 60%
78
Quality 40%
32
Run on models
none yet
Process rating
C
63/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
30
Running it twice w 4
30
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. Shorten the description to 1024 characters.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Exfiltration exfil-webhook-url wrappers/paired-call-handler.py:217
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    f"https://api.telegram.org/bot{token}/sendMessage",
    quoted
  • medium Exfiltration exfil-webhook-url wrappers/paired-inbox-hook.py:176
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    url = f"https://api.telegram.org/bot{token}/sendMessage"
    quoted
  • medium Exfiltration exfil-webhook-url wrappers/paired-respond.py:410
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    url = f"https://api.telegram.org/bot{token}/sendMessage"
    quoted
  • medium Exfiltration exfil-webhook-url wrappers/paired-sms-command-hook.py:133
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    url = f"https://api.telegram.org/bot{token}/sendMessage"
    quoted
  • low Exfiltration exfil-webhook-url wrappers/paired-call-watch-tg-hook.sh:95
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    -X POST "https://api.telegram.org/bot${TG_BOT_TOKEN}/sendMessage" \
    placeholder
  • low Exfiltration exfil-webhook-url wrappers/paired-sms-watch-tg-hook.sh:66
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    -X POST "https://api.telegram.org/bot${TG_BOT_TOKEN}/sendMessage" \
    placeholder

Files scanned: 65. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • error description-long description is 1274 chars, limit 1024
  • 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: Paired: Phone Agent. Bridges an OpenClaw agent to the user's own p… ^ ); 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 "capabilities"
  • note frontmatter-key unknown frontmatter key "requires"
  • note frontmatter-key unknown frontmatter key "safety"

Process rating: all ten parameters 63/100

  • 0Result and completion. Does not say what the result is
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 27 mutating operations with no state check
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 4262 tokens
  • 100Steps. 37 steps
  • 100Failures and branches. 3 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (7 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Description length 1274: 120–800 characters recommended
  • +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
  • +5Description quotes 20 example trigger phrases
  • +4Structure: 24 headings
  • +3Step-by-step instructions: 37 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 32.

External checks

ClawHub: suspicious
The skill is broadly aligned with controlling a user-owned phone, but it under-discloses several automatic SMS/call behaviors and lacks the promised trust gate on some SMS paths.
LLM: suspicious (high) · VirusTotal: · 29 May 2026