Host security hardening and risk-tolerance configuration for OpenClaw deployments.
SkillScore78Maintained
Automatic
◆Security & AppSec pack
Last verified 9/28/2026
What it changes
Passed 21 of 27 test cases with the skill, and 9 of 27 without it.
Without skill33%
With skill78%
Checks it passed that the model alone missed
Lists needed follow-up items as an unordered list.
Uses healthcheck:security-audit as the cron job name.
Uses openclaw cron edit when updating an existing job.
and 14 more in the full report
13 fixed8 passed either way5 still failing1 broke
Pass-rate lift
+44 pp
Tokens
+64%
Agent turns
0%
Response time
-48%
Model gemini-3.6-flashMeasured 9/28/2026v121 of 27 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
What exact OpenClaw CLI command should be executed during read-only health checks to determine release channel and update availability?
What was checked, without and with the skill
Checked
Without skill
With skill
Executes openclaw update status to check update availability.
Missed
Passed
case-15 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md240 linessingle file
OpenClaw Host Hardening
Overview
Assess and harden the host running OpenClaw, then align it to a user-defined risk tolerance without breaking access. Use OpenClaw security tooling as a first-class signal, but treat OS hardening as a separate, explicit set of steps.
Core rules
Recommend running this skill with a state-of-the-art model (e.g., Opus 4.5, GPT 5.2+). The agent should self-check the current model and suggest switching if below that level; do not block execution.
Require explicit approval before any state-changing action.
Do not modify remote access settings without confirming how the user connects.
Prefer reversible, staged changes with a rollback plan.
Never claim OpenClaw changes the host firewall, SSH, or OS updates; it does not.
If role/identity is unknown, provide recommendations only.
Formatting: every set of user choices must be numbered so the user can reply with a single digit.
System-level backups are recommended; try to verify status.
Workflow (follow in order)
0) Model self-check (non-blocking)
Before starting, check the current model. If it is below state-of-the-art (e.g., Opus 4.5, GPT 5.2+), recommend switching. Do not block execution.
1) Establish context (read-only)
Try to infer 1–5 from the environment before asking. Prefer simple, non-technical questions if you need confirmation.
Determine (in order):
OS and version (Linux/macOS/Windows), container vs host.
Disk encryption status (FileVault/LUKS/BitLocker).
OS automatic security updates status.
Note: these are not blocking items, but are highly recommended, especially if OpenClaw can access sensitive data.
Usage mode for a personal assistant with full access (local workstation vs headless/remote vs other).