node-connect
v1.0.0Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi w...
⭐ 0· 1.2k·61 current·61 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description match the actions in SKILL.md: it queries OpenClaw configuration, QR/setup payloads, nodes/devices status, and (when relevant) Tailscale state. None of the declared or implied requirements (no env vars or installs) are unexpected for a CLI-based diagnostic guide.
Instruction Scope
Instructions explicitly tell the agent to run openclaw CLI commands (openclaw config get, qr --json, devices list/approve, nodes status) and tailscale status. These are appropriate for diagnosing pairing/connectivity. Note: some suggested commands are state-changing (e.g., openclaw devices approve --latest) — this is within the skill's purpose but has side effects and should be run with user consent.
Install Mechanism
Instruction-only skill with no install spec or code files. Lowest-risk delivery mechanism; nothing is downloaded or written by the skill itself.
Credentials
The skill requests no environment variables or external credentials. It does rely on local CLIs (openclaw, optionally tailscale) being present; those CLIs will access local config/state, which is expected for this diagnostic task.
Persistence & Privilege
always:false and no install means no permanent presence. However, because the instructions include commands that modify system state (approving devices, changing gateway settings), allow-listing autonomous invocation could let the agent perform those actions without additional prompts. That risk arises from the platform default of autonomous invocation, not from the skill itself.
Assessment
This skill is coherent for diagnosing OpenClaw pairing/connectivity. Before installing or invoking it: 1) Confirm the agent environment actually has the openclaw CLI (and tailscale if relevant); the skill expects to run those commands. 2) Be aware some suggested commands are state-changing (e.g., openclaw devices approve --latest or changing gateway.bind/mode). Only allow the agent to run those if you trust it to make configuration changes. 3) If you want to avoid unintended changes, require the agent to ask for explicit approval before running write/approve commands. 4) If you have sensitive network or auth concerns, run the commands yourself or in a controlled/test environment and paste outputs for diagnosis instead of granting the agent autonomous execution.Like a lobster shell, security has layers — review code before you run it.
latestvk972kpxkxq9br0t5fzgd03rvds83kcm3
License
MIT-0
Free to use, modify, and redistribute. No attribution required.