Works with the AI Agents you already use
Host Hardening Audit
Audit a server or workstation's security posture with read-only checks, then apply staged hardening. Use when a host needs an SSH, firewall, update, backup, and
Free
Host Hardening Audit
Example session with this skill installed
I just spun up a new Ubuntu VPS on DigitalOcean. I need to make sure it's secure before I point my domain at it. Can you run a hardening audit?
- Read your context and instructions
- Compiled the host hardening audit
Audit complete. Found 2 Critical issues: Root SSH password login is enabled, and MySQL is listening on all interfaces.
Proposed plan
- Update packages
- Whitelist your current IP in UFW
- Setup SSH keys and disable passwords
- Bind MySQL to localhost
Shall I proceed?
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Exposing a server to the internet without a verified security baseline invites automated brute-force attacks and lateral movement. Manually checking SSH configs, firewall rules, and listening ports is error-prone and often leads to accidental lockouts.
What it does
- Performs a non-destructive, read-only audit of OS versions, listening services, and firewall states.
- Categorizes findings into critical, important, and advisory risk buckets based on exposure.
- Implements hardening steps in a reversible order, prioritizing connectivity persistence.
- Verifies every change with before-and-after command diffs to ensure the intended posture.
- Generates a final report with actions taken, rollback instructions, and remaining risks.
Frameworks & tools
Linux distributions (Ubuntu, Debian, RHEL, CentOS), SSH, UFW, Firewall-cmd, nftables, systemd, and fail2ban.
Why this beats prompting it yourself
A standard LLM might suggest dangerous firewall commands that drop your current session. This skill enforces a "test-before-lock" workflow, requiring verification of new SSH keys and admin IP whitelisting before disabling legacy access or applying default-deny rules.
Use cases
- Preparing a fresh VPS or bare-metal server for its first public IP exposure.
- Conducting a post-incident review to identify stale users or unauthorized listeners.
- Performing periodic security hygiene passes on a fleet of small servers.
- Hardening a development box before deploying a reverse proxy or tunnel.
Known limitations
Not a replacement for full CIS or STIG compliance suites. Requires read-only shell access to execute audit commands.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Security.
Requires shell access for command execution. Does not replace formal CIS/STIG compliance frameworks. Assessment is limited to the local host environment.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
4 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account