Works with the AI Agents you already use
Wazuh Fullstack AI
Deploy and manage a full Wazuh security stack with local AI alert analysis and automated Windows agent orchestration.
$15
Wazuh Fullstack AI
Example session with this skill installed
Inspect my current Wazuh stack and analyze the latest alert from the fixtures folder.
- Read your context and instructions
- Compiled the wazuh fullstack ai
I have completed the stack inspection and processed the requested alert. The stack is healthy, though the agent connection is currently idle.
Stack Status & Alert Analysis
| Component | Status | Details |
|---|---|---|
| Docker Containers | UP | Manager, Indexer, and Dashboard are running |
| Wazuh API | ACTIVE | Responding on port 55000 |
| Windows Agent | RUNNING | WazuhSvc is active (PID: 4820) |
| Local AI (Laya) | READY | ONNX provider initialized |
| Local AI (Ollama) | READY | Model qwen2.5:7b loaded |
Alert Triage Result: alert_20231012_01.json
- Decision: CRITICAL
- Confidence: 0.94
- Routing: Sent to Ollama for summarization
Summary: Multiple failed RDP login attempts detected from IP 192.168.1.45 targeting the Administrator account. This indicates a potential brute-force attack.
Recommendation: Validate if this IP belongs to an authorized user. If not, consider blocking the IP at the firewall level and enforcing MFA for RDP sessions.
Next steps
- Review the detailed incident entry in
wazuh-incidents.db. - Execute
connect-agent-manager.ps1if you need to refresh the agent's connection strings. - Run
inspect-stack.pyagain after any network configuration changes.
Connects securely to your tools. The creator never sees your data.
About this skill
Managing a security operations stack requires constant switching between infrastructure management, agent configuration, and alert triage. This skill automates the lifecycle of a Wazuh full-stack environment, integrating local AI to filter and summarize security events without sending sensitive data to the cloud.
What it does
- Automated Stack Deployment installs the Wazuh manager, indexer, and dashboard using Docker via PowerShell scripts.
- Hybrid AI Alert Triage utilizes a two-tier pipeline with Laya/ONNX for fast noise filtering and Ollama for detailed summarization.
- Secure Agent Provisioning connects Windows agents to the manager with mandatory configuration backups and auto-restoration.
- Stack Inspection performs multi-layer health checks across Docker, the Wazuh API, and agent services to diagnose connectivity gaps.
- Incident Logging records critical alerts and stack changes into a local SQLite database for auditability.
How it works
- Run Inspection using
inspect-stack.pyto establish the current state of Docker containers, services, and AI models. - Execute Deployment with
install-manager-docker.ps1using the--dry-runflag to review the plan before giving the final execution command. - Connect Agents by running the connection script which handles protocol negotiation and
ossec.confupdates. - Process Alerts through the automated pipeline which routes JSON events to local models for classification and summary.
Frameworks & tools
The skill utilizes Docker for containerized infrastructure and PowerShell for Windows host management. The AI pipeline runs locally via Ollama (qwen2.5:7b) and Laya/ONNX, storing data in SQLite and SiYuan.
Why this beats prompting it yourself
Manual Wazuh orchestration often leads to broken agent-manager protocols and inconsistent alert handling. This skill enforces mandatory dry-runs, automated backups, and a resource-efficient AI routing logic that prevents high GPU usage on low-priority noise.
Use cases
- Deploying a local SOC environment for testing or small-scale production.
- Automating the triage of high-volume security alerts using local LLMs.
- Diagnosing why a Windows endpoint is not appearing as "Active" in the dashboard.
- Maintaining an append-only audit log of all infrastructure changes.
Known limitations
Does not perform automatic remediation like IP blocking or process isolation. Requires elevated privileges for Windows service management and specific PowerShell syntax handling for Docker.
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.
No auto-remediation (suggestions only). Requires elevated privileges for ossec.conf. Docker scripts require PowerShell 5.1 compatibility. AI summary requires local GPU/Ollama.
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
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 29 days ago
- Software
Python 3.10+PowerShell 5.1+Docker Desktop
Git
- Optional
- OllamaLaya/ONNXPython
Permissions
This skill operates entirely on localhost. It reads its own scripts/references/fixtures and modifies ossec.conf with mandatory backup before any change. No cloud calls, no telemetry. Docker is used for Wazuh deployment. Ollama and Laya are optional local AI providers.