← Back to Skills Marketplace
53
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install yihui-healthcheck
Description
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, r...
Usage Guidance
This skill is internally consistent with a host-hardening audit for OpenClaw and is instruction-only (no installers or credential requests). Before running it: (1) allow only the read-only checks unless you explicitly approve fixes; (2) review the exact commands the agent proposes to run, especially ones that require root or that change system state; (3) be cautious about running any '--fix' actions without backups and a rollback plan; and (4) remember autonomous invocation is allowed by platform default — don't give blanket permission for state changes to an agent you don't fully trust.
Capability Analysis
Type: OpenClaw Skill
Name: yihui-healthcheck
Version: 1.0.1
The yihui-healthcheck skill is a legitimate security utility designed for host hardening and risk assessment of OpenClaw deployments. It follows a transparent workflow in SKILL.md, requiring explicit user approval for system information gathering (e.g., using uname, ss, lsof) and any state-changing actions like firewall modifications or cron scheduling. The code relies on standard OpenClaw CLI commands and lacks any indicators of data exfiltration, obfuscation, or unauthorized persistence.
Capability Assessment
Purpose & Capability
Name/description (host hardening for OpenClaw) match the actions the skill instructs the agent to take: OS/fingerprint checks, listening ports, firewall state, backups, and running OpenClaw CLI audits and status checks.
Instruction Scope
SKILL.md directs the agent to run a set of read-only system commands (uname, /etc/os-release, ss/lsof, firewall tooling, tmutil, openclaw audits) which are appropriate for a host-hardening assessment. The skill explicitly requires user approval before any state-changing actions. Note: some read-only commands (e.g., ss -p, lsof, or certain firewall queries) can reveal process and network details and may require elevated privileges to be fully informative; the doc asks the agent to infer privilege and ask first.
Install Mechanism
No install spec or code files — instruction-only. Nothing will be written to disk by an installer. This is the lowest-risk install posture.
Credentials
The skill declares no required environment variables, no primary credential, and no config paths. The data it asks to read (OS/version, network exposure, backups, OpenClaw status) is directly relevant to host hardening.
Persistence & Privilege
always:false and no install — the skill does not request permanent presence or elevated platform privileges. It can be invoked autonomously by the agent (platform default); combined with the skill's ability to recommend state changes, you should ensure explicit confirmation is required before applying fixes (the SKILL.md already requires explicit approval).
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install yihui-healthcheck - After installation, invoke the skill by name or use
/yihui-healthcheck - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
Initial release
v1.0.0
Initial release
Metadata
Frequently Asked Questions
What is YiHui Healthcheck?
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, r... It is an AI Agent Skill for Claude Code / OpenClaw, with 53 downloads so far.
How do I install YiHui Healthcheck?
Run "/install yihui-healthcheck" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is YiHui Healthcheck free?
Yes, YiHui Healthcheck is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does YiHui Healthcheck support?
YiHui Healthcheck is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created YiHui Healthcheck?
It is built and maintained by 辉哥 (@1yihui); the current version is v1.0.1.
More Skills