← Back to Skills Marketplace
lotfinity

gateway-control-ui

by lotfinity · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
313
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install gateway-control-ui
Description
Step-by-step guide to log into the OpenClaw Control UI, enter gateway token, approve device pairing, and verify connection
README (SKILL.md)

Gateway Control UI Login & Pairing

Use when a user needs to access the OpenClaw Gateway Control UI, authenticate, pair a device, and confirm connectivity.

Prerequisites

  • OpenClaw gateway running (openclaw status)
  • Control UI URL configured in gateway.controlUi.allowedOrigins
  • Gateway token available in config (/data/.openclaw/openclaw.json)
  • Device pairing approval (CLI)

Steps

1. Open Control UI

  • URL: use your configured OpenClaw service URL (from gateway.controlUi.allowedOrigins)
  • HTTP Basic Auth:
    • Username: use your SERVICE_USER_OPENCLAW value
    • Password: use your SERVICE_PASSWORD_OPENCLAW value
  • Optional embedded form:
    • https://\x3Cuser>:\x3Cpass>@\x3Cyour-openclaw-domain>/

2. Get Gateway Token

cat /data/.openclaw/openclaw.json | grep -A 2 '"token"'

Token is under:

"gateway": { "auth": { "token": "YOUR_TOKEN_HERE" } }

3. Enter Token in UI

  • On Overview page, click Gateway Token field
  • Paste token
  • Click Connect

4. Approve Pairing (CLI)

openclaw devices list
openclaw devices approve \x3CrequestId>

5. Verify Success

  • In Control UI: status shows green “OK” and dashboard loads
  • CLI:
    openclaw status --deep
    
    Check Gatewayreachable and channels show OK.

Troubleshooting

  • Page stays on form? WebSocket URL may need to be filled (usually left blank for remote)
  • Pairing fails? Run openclaw devices list again to see pending requests
  • Token invalid? Check /data/.openclaw/openclaw.json for correct value
Usage Guidance
This skill appears to genuinely guide UI login and pairing, but it instructs reading a local config file (/data/.openclaw/openclaw.json) and using credentials (SERVICE_USER_OPENCLAW / SERVICE_PASSWORD_OPENCLAW) that are not declared in the metadata. Before installing or allowing autonomous use: (1) prefer running these steps manually rather than giving an agent automatic filesystem/auth access; (2) do not embed credentials in URLs — use the UI's login form or a secure credential store; (3) ask the publisher to update the skill metadata to declare required config paths and env vars so you can judge what will be accessed; (4) if you must run via the agent, restrict its permissions so it can only read the specific config file and nothing else, and audit logs for access to secrets.
Capability Analysis
Type: OpenClaw Skill Name: gateway-control-ui Version: 1.0.0 The skill bundle provides a legitimate administrative workflow for authenticating and pairing an OpenClaw gateway. It guides the agent to retrieve a gateway token from a local configuration file (/data/.openclaw/openclaw.json) and use the 'openclaw' CLI to approve device requests. The instructions are consistent with the stated purpose of system configuration and do not contain evidence of malicious intent, data exfiltration to external domains, or unauthorized execution.
Capability Assessment
Purpose & Capability
The skill's described purpose (UI login, paste gateway token, approve pairing) aligns with the commands shown (openclaw CLI, cat). However the SKILL.md requires reading /data/.openclaw/openclaw.json and using SERVICE_USER_OPENCLAW/SERVICE_PASSWORD_OPENCLAW values while the manifest declares no required config paths or env vars — an inconsistency that should be explained.
Instruction Scope
The runtime instructions explicitly tell an agent to read a host filesystem path (/data/.openclaw/openclaw.json) and to use credential values (SERVICE_USER_OPENCLAW, SERVICE_PASSWORD_OPENCLAW) that are not declared. It also suggests embedding user:pass in a URL (https://user:pass@...), which is insecure. These steps can expose secrets and grant access to sensitive state; they extend beyond purely UI navigation guidance.
Install Mechanism
No install spec and no code files — instruction-only reduces installation risk. Declared required binaries (openclaw, cat) are reasonable for the task.
Credentials
The skill declares no required environment variables or config paths, yet the instructions reference SERVICE_USER_OPENCLAW, SERVICE_PASSWORD_OPENCLAW, and a specific config file path containing the gateway token. Requesting access to those secrets/configs would be proportionate to the task, but the omission in metadata is a mismatch and makes it unclear what the skill expects to access.
Persistence & Privilege
always:false and no install activity; the skill does not request persistent presence or modifications to other skills. Autonomous invocation is allowed (platform default) but is not combined here with unusual privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install gateway-control-ui
  3. After installation, invoke the skill by name or use /gateway-control-ui
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
0.1.0
Metadata
Slug gateway-control-ui
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is gateway-control-ui?

Step-by-step guide to log into the OpenClaw Control UI, enter gateway token, approve device pairing, and verify connection. It is an AI Agent Skill for Claude Code / OpenClaw, with 313 downloads so far.

How do I install gateway-control-ui?

Run "/install gateway-control-ui" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is gateway-control-ui free?

Yes, gateway-control-ui is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does gateway-control-ui support?

gateway-control-ui is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created gateway-control-ui?

It is built and maintained by lotfinity (@lotfinity); the current version is v1.0.0.

💬 Comments