Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
secucheck 2.8.0 - Improved handling and documentation for failed security checks by adding platform-specific fallback commands. - Enhanced cross-platform compatibility with clearer instructions for Linux, macOS, WSL, Windows, and DSM environments. - Expanded agent instructions on fallback procedures for minimal environments and missing tools. - Documentation updates in SKILL.md for platform detection fields and fallback workflow. - No core features changed; this is a workflow and documentation enhancement release.
What This Skill Does
secucheck runs read-only security audits on OpenClaw deployments. It scans 7 domains including runtime, agents, channels, cron jobs, skills, sessions, and network exposure. Results are presented at three expertise levels with a visual HTML dashboard.
Covers all major OpenClaw attack surfaces in a single command instead of manually reviewing each config domain separately.
When to use it
- Running a weekly security check on a self-hosted OpenClaw instance
- Reviewing agent permissions after adding a new tool with exec access
- Auditing cron job configurations before a production deployment
- Getting a beginner-friendly explanation of network exposure risks
- Generating a shareable HTML security report for a team review
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: run a full security audit
- 1Prompts user to select an expertise level (beginner, intermediate, or expert)
- 2Runs full_audit.sh to collect configuration and runtime data as JSON
- 3Parses findings and groups them by category and severity
- 4Formats the report in the user's language at the chosen detail level
- 5Runs serve_dashboard.sh and returns the HTML dashboard URL
Text report with severity counts grouped by domain (runtime, agents, channels, etc.) and a browser-accessible HTML dashboard at the local network IP