Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    OpenClaw Setup Hardening Automation Pack

    1

    Secure, harden, and automate your OpenClaw Gateway with production-grade security tiers and daily cron routines.

    $15

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    OpenClaw Setup Hardening Automation Pack

    OpenClaw Setup Hardening Automation Pack

    Example session with this skill installed

    I just installed OpenClaw on a Raspberry Pi. I want to make sure it is secure and I need a morning brief scheduled for 8 AM.

    • Read your context and instructions
    • Compiled the openclaw setup hardening

    I will begin the onboarding and hardening process for your Raspberry Pi setup. I'll start with a discovery check to verify the environment before applying Recommended tier security controls and scheduling your morning brief.

    Discovery and Initial Audit

    I have performed a read-only scan of the environment. The gateway is currently running as root, which is a high-risk finding for a Pi-based setup.

    MetricStatus
    OSLinux (Raspbian)
    OpenClaw Versionv0.8.2
    Gateway Bind0.0.0.0 (Exposed)
    Auth StatusDisabled
    Health Check2 warnings found

    Security Hardening Plan

    I have prepared the following hardening commands to lock down the instance.

    
    # 1. Restrict gateway to loopback only
    openclaw config set gateway.bind loopback
    
    # 2. Enable authentication and set reference to env var
    openclaw config set-ref gateway.auth.token env OPENCLAW_TOKEN
    
    # 3. Secure the state directory
    chmod 700 ~/.openclaw
    chmod 600 ~/.openclaw/openclaw.json
    
    # 4. Schedule the Morning Brief (08:00 daily)
    openclaw cron add --name "Morning brief" --cron "0 8 * * *" --tz "Europe/London" \
      --session isolated --announce --channel telegram --to "admin" --tools read \
      --message "Prepare a brief for today: calendar prep and urgent alerts. Max 8 lines."
    

    Setup Report Summary

    The instance is transitioning to

    Recommended tier. The binding change will prevent external network scans from hitting your gateway port. The morning brief is configured in an isolated session, meaning it cannot modify its own schedule or security settings.

    Next steps

    1. Run export OPENCLAW_TOKEN=$(openssl rand -hex 32) and add it to your .bashrc or service file.
    2. Confirm the Telegram channel ID for delivery.
    3. Approve the openclaw gateway restart to apply the loopback binding.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Deploying a self-hosted agent gateway like OpenClaw introduces significant surface area for remote-control attacks and prompt injection. This skill provides a guided, safety-first workflow to transition from an unconfigured install to a locked-down, self-monitoring production environment. It prioritizes read-only inspection, least-privilege configuration, and verifiable security tiers to ensure your personal agent remains under your control.

    What it does

    • Gateway hardening implements binding to loopback, secret references via environment variables, and strict file system permissions.
    • Security auditing runs built-in deep checks and applies the tier-based hardening checklist (Baseline, Recommended, or Strict).
    • Automation scheduling configures morning briefs, nightly health checks, and weekly security reports using native cron and heartbeat primitives.
    • Skill vetting provides a structured framework for reviewing third-party plugins and skills for malicious patterns or data exfiltration.
    • Incident response offers a dedicated recovery protocol for suspected compromises, including service suspension and credential rotation.

    How it works

    1. Discovery executes a compact discovery phase to detect OS, host type, and existing configuration health.
    2. Hardening applies the selected security tier (Baseline, Recommended, or Strict) and verifies results with openclaw security audit.
    3. Automation sets up isolated cron jobs and HEARTBEAT.md tasks for proactive monitoring.
    4. Reporting delivers a final Setup Report with a hardening scorecard and maintenance calendar.

    Frameworks & tools

    This skill is designed for OpenClaw Gateways running on Linux, macOS (Mac mini/laptop), Raspberry Pi, or Docker. It utilizes node.js, systemd, launchd, and the openclaw CLI.

    Why this beats prompting it yourself

    Generic prompts often ignore the risk of agents rewriting their own security configs or failing to handle secrets as environment references. This skill enforces a non-negotiable "read-only first" policy and uses precise CLI commands over manual JSON editing to prevent gateway start failures.

    Use cases

    • Secure a new install on a home server or VPS to prevent unauthorized remote access.
    • Audit existing setups to identify plaintext keys or overly permissive tool access.
    • Build daily routines like morning briefs and nightly health checks without manual prompting.
    • Vet third-party skills for hidden network calls or obfuscated code before installation.

    Known limitations

    Requires a functional Node.js environment. Deep hardening on Windows/WSL may have limited daemon support compared to native Linux or macOS.

    Requires Node.js environment. Daemon support varies by OS. Security audit cannot guarantee 100% protection against zero-day injection. Manual approval required for destructive CLI fixes.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Openclaw
    Node.js
    macOS

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    openclaw.ai
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill transforms a standard OpenClaw install into a production-grade environment by automating security configurations, such as loopback binding and environment variable masking, while establishing automated daily maintenance routines.

    The pack includes three predefined security tiers—Baseline, Recommended, and Strict—allowing you to choose the level of restriction that best fits your specific hardware and use case.

    It is optimized for Linux, macOS, Raspberry Pi, and Docker environments; however, users running OpenClaw on Windows/WSL may experience limited support for certain background daemon and cron features.

    No, the skill enforces a 'read-only first' policy and uses specific CLI commands to prevent the agent from accidentally overwriting its own security configurations or breaking the gateway.

    You receive the full automation workflow, the vetting framework for third-party skills, an incident response protocol, and the structured logic for setting up morning briefs and nightly health checks.

    New in Agents & Orchestration