
from openclaw-skills-security62
Audit an OpenClaw installation and generate a prioritized, ready-to-apply hardening plan for AGENTS.md, gateway, sandbox, and permissions.
Config Hardener audits an OpenClaw project for common security misconfigurations and produces clear, prioritized hardening recommendations plus ready-to-use config templates (e.g. AGENTS.md and .openclaw settings). It inspects AGENTS.md, gateway settings, sandbox and permission policies and outputs findings with remediation steps and diffs you can review.
Run this skill before enabling broad or untrusted skill usage on a host, when onboarding new repositories, or after upgrading OpenClaw. Use it to generate templates when AGENTS.md is missing or to verify gateway and sandbox settings after deployment.
Works with CLI-driven agent environments and LLM-based execution layers (Codex/Claude/GPT-like toolchains) that can read repository files and present diffs. It is repository-agnostic and intended for OpenClaw deployments and operator workflows.
This skill has not been reviewed by our automated audit pipeline yet.