CentOS Stream 10 with Cockpit and AI Security Assistant
Madarson It, LLC · Cybersecurity & IT
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 7 captures on record
What the publisher says
As described on Microsoft Marketplace.
This Azure-based virtual machine is pre-configured with CentOS Stream 10 and includes the Cockpit web console and an AI-powered Security Assistant backed by Anthropic Claude.
This image combines two capabilities in one. Cockpit gives you a clean browser-based interface to manage your server without needing SSH for every task. The AI Security Assistant analyzes your live system using Anthropic Claude and returns prioritized security findings, remediation commands, and compliance observations on demand.
Show the rest of the publisher’s description (28 more lines)
Cockpit Web Console
Monitor CPU, memory, disk, and network in real time, manage services, review logs, manage user accounts, configure networking, manage Podman containers, apply software updates, and access a full terminal in the browser -- no SSH client required.
AI Security Assistant
Powered by Anthropic Claude, the Security Assistant analyzes your live system across six analysis types -- Full Security Audit, SSH Review, Audit Log Analysis, Services Review, Network Review, and User Account Review. Results include an Executive Summary, severity-rated Findings, numbered Recommendations, and compliance observations mapped to PCI-DSS, HIPAA, and NIST. The Ask AI tab answers plain-language questions with specific commands based on your actual system.
The Security Assistant uses your own Anthropic API key. Your key is stored only in your browser and never sent to Madarson IT.
Key Features
- Cockpit web console for browser-based server management
- AI Security Assistant powered by Anthropic Claude
- Six security analysis types with severity-rated findings
- Plain-language Ask AI with live system-aware responses
- Your own API key -- no vendor data retention
- Full browser terminal and Podman management included
- SELinux enforcing by default for additional access protection
Ideal For
- Administrators who want browser-based management without deep CLI expertise
- Organizations wanting AI-assisted security analysis without a SaaS platform
- SMBs running Linux workloads who need on-demand security guidance
- DevOps teams wanting a management console with built-in AI security feedback
Quick Start
- Deploy the VM and SSH in using your SSH key
- Set a Cockpit password: sudo passwd $(whoami)
- Open port 9090 in your Network Security Group
- Navigate to your instance IP on port 9090 in a browser
- Log in and click Security Assistant in the left navigation
- Enter your Anthropic API key in Settings and run an analysis
Disclaimer
CentOS is a trademark of Red Hat, Inc. Madarson IT does not provide commercial licenses for CentOS, Red Hat, or third-party software. Claude is a third-party AI service billed directly to your Anthropic account and subject to Anthropic's Terms of Service.
To speak with us about private offers, custom security requirements, or compliance needs, contact us at info@madarsonit.com
Preview
5 images
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Sources
Publisher resources
5 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.