Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    OpenClaw Security Audit: Harden Your Always-On Agent

    1

    OpenClaw is the most-starred agent project on GitHub, and most installs run 24/7 with access to your chats, your files and a shell.

    $19

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    OpenClaw Security Audit: Harden Your Always-On Agent

    OpenClaw Security Audit: Harden Your Always-On Agent

    Example session with this skill installed

    Run a security audit on my OpenClaw install on my home server. It's connected to Telegram and my Gmail, and I installed three skills from ClawHub last week.

    • Read your context and instructions
    • Compiled the openclaw security audit

    Summary

    OpenClaw 2026.10.7 on homeserver-01.

    VERDICT: EXPOSED. One injection path reaches host shell with no approval, and the web gateway is reachable through a public tunnel.

    Checks

    #CheckResultEvidence
    1Inbound accessWARNTelegram limited to your user ID; Gmail channel acts on any sender (Gmail channel section of your config)
    2Execution powerFAILHost exec enabled, approvals set to always-allow (exec settings in your config)
    3Skills supply chainFAILquick-notes-sync runs a base64 blob that posts ~/.openclaw to an outside URL (scripts/sync.sh:14)
    4Gateway exposureFAILGateway bound to all interfaces and shared through a public tunnel
    5SecretsWARNAPI keys in plaintext config, permissions 644 (should be 600)
    6Autonomous behaviorWARNMorning heartbeat reads inbox and can send replies without approval
    7SpendOKProvider key has a monthly cap
    8Logging and updatesOKCurrent release, tool calls logged

    Injection paths

    • Any email → model → shell on host → NOT STOPPED
    • Web fetch → model → send Telegram message → stopped by approval

    Fix plan (most risk removed first)

    1. Remove quick-notes-sync, then rotate the model key and Telegram token (ending ...4f2a, ...91c0). 2 min.
    2. Switch exec approvals to ask, and run exec in the sandbox container. Diff provided. 3 min.
    3. Restrict the Gmail channel to an allowlist of your two addresses. 1 min.
    4. Bind the gateway to 127.0.0.1 and remove the public tunnel; use private network access instead. 2 min.
    5. chmod 600 the config file. 10 sec.

    Re-run after fixes: expected verdict SAFE.

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

    About this skill

    OpenClaw is the most-starred agent project on GitHub, and most installs run 24/7 with access to your chats, your files and a shell. That is a different risk class from a coding assistant you watch: one message in a group chat, one email, or one ClawHub skill with hidden instructions can make it act for someone else.

    This skill audits your install the way an attacker would look at it, then tells you exactly what to change.

    What it checks (8 areas, each OK / WARN / FAIL with the file and line it read):

    1. Inbound access: every channel (WhatsApp, Telegram, Discord, Slack, iMessage, email) and who can send messages it will act on
    2. Execution power: shell on host or sandbox, approvals, write and delete reach, signed-in browser profiles
    3. Skills supply chain: reads every installed skill for hidden instructions, remote code, secret grabs, invisible Unicode
    4. Gateway exposure: bind address, auth, tunnels, firewall
    5. Secrets: where keys and tokens live, file permissions, whether the agent itself can read them
    6. Autonomous behavior: cron jobs, heartbeats and webhooks that act with nobody watching
    7. Spend and blast radius: API caps, payment or messaging tools, worst single-run cost
    8. Logging and updates: would you notice an incident, and is your version patched

    Plus a prompt-injection walk-through: for every channel and every tool that reads outside content, it traces the worst action an injected instruction could reach and whether an approval or sandbox stops it.

    You get: an inventory of your install, the eight checks, the injection paths, a fix plan ordered by risk removed per minute of work (each fix as an exact diff or command plus how to verify it), and a SAFE / HARDEN / EXPOSED verdict.

    Built to be safe itself: read-only until you approve each fix, never prints secrets (last 4 characters only), and never assumes a config key it didn't read, because OpenClaw's layout changes between releases. If your version has a built-in security or doctor command, it runs that first and folds the results in.

    Works with Claude Code, Codex CLI, Cursor, Gemini CLI and other SKILL.md agents, run on the machine (or over SSH to the machine) where OpenClaw is installed.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Only audits local or accessible filesystem configs. Does not perform active network penetration testing or certify legal compliance. Requires read access to OpenClaw config directories.

    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 buying a skill.

    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 19 days ago

    Permissions

    Network Access
    Read Files
    Write Files
    Terminal / Shell
    Listed19 days ago

    What's inside

    Frequently Asked Questions

    No. It is read-only by default. Every fix is shown as an exact diff or command, and it only applies one after you say yes.

    It locates your actual config files and reports only what they show, because the layout changes between releases. If your version has a built-in security or doctor command, it runs that first and includes the results.

    No. When it finds a secret, it reports where it lives and only the last 4 characters.

    No. It is a structured security review of your own install. Only use it on machines you own or are allowed to audit.

    Any agent that supports the SKILL.md standard, including Claude Code, Codex CLI, Cursor and Gemini CLI, running on or connected to the machine where OpenClaw is installed.

    New in Agents & Orchestration