OpenClaw Module 3: Security & Permissions

Goal: turn OpenClaw security guidance into a concrete checklist you can run and rerun in CI or ops playbooks.

Run audits in a controlled environment first. Treat findings as input to your org’s own security review, not a full replacement.

Hands-on Steps (Directly Runnable)

Execute each command, capture output, then note issues and fixes.

Step 1: Run a baseline security audit

Start with a human-readable report:
openclaw security audit

For deeper checks (DM scopes, sandbox, hooks, webhooks, plugins):
openclaw security audit --deep

Skim the summary and note any high or critical warnings (shared DM scopes, open group policies, sandbox disabled with browser tools, etc.).

Copyable commands
openclaw security audit
openclaw security audit --deep

Step 2: Export findings for CI / policy checks

Produce JSON output you can feed into scripts:
openclaw security audit --json | jq ' .summary '
openclaw security audit --deep --json | jq ' .findings[] | select(.severity=="critical") | .checkId '

Store these reports under your ops or security repository so you can track drift over time.

Copyable commands
openclaw security audit --json | jq ' .summary '
openclaw security audit --deep --json | jq ' .findings[] | select(.severity=="critical") | .checkId '

Step 3: Apply safe automatic fixes where possible

Let OpenClaw apply deterministic remediations:
openclaw security audit --fix

Or combine with JSON output:
openclaw security audit --fix --json | jq ' {fix: .fix.ok, summary: .report.summary} '

--fix focuses on safe changes: tightening file permissions, enabling logging.redactSensitive, closing obvious group-policy oversharing, etc. It does not remove plugins, rotate keys, or change gateway exposure on its own.

Copyable commands
openclaw security audit --fix
openclaw security audit --fix --json | jq ' {fix: .fix.ok, summary: .report.summary} '

Step 4: Re-run `openclaw doctor` after fixes

After applying fixes, run:
openclaw doctor --deep

Confirm that gateway, sandbox, and channels all look healthy, and that any remaining warnings are either acceptable or queued for manual remediation.

Copyable commands
openclaw doctor --deep

Continue to the next module

Turn the commands on this page into your team runbook.

OpenClaw Module 3: Security & Permissions | BestClaw