AI Defense Matrix Catalog

Jozu

Visit official site

Overview

Product details compiled from public sources, each with a citation.

Vendor
Jozu3 · Details at Cyber Company Profiles
Description
On-prem AI model registry that secures the model supply chain by scanning, signing, and tamper-proof packaging models, agents, and MCP servers, built on the open-source KitOps project.3
Deployment
Self-hosted3
Status
Active1

Matrix Coverage

Where this product defends, by asset class and NIST CSF function. The Coverage column shows whether each asset is Primary, Secondary, or Adjacent to what the product does. The table omits empty rows and columns.

Asset class IdentifyProtectDetect Coverage
AI Coding and Orchestration Tools Secondary 4
AI Model Primary 2

Framework Relevance

These frameworks include controls relevant to the asset classes Jozu defends. This is an editorial inference from the AI Defense Matrix asset-level crossmap, not a statement that Jozu implements these controls or is certified against them.

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI Coding and Orchestration Tools Agents as deployed artifacts (orchestration view; see AI Agent Identities row for the principal view); system prompts and templates
AI Model Models; Algorithms (model configuration)
CSA AI Controls Matrix AI Coding and Orchestration Tools Application and Interface Security; Supply Chain Management
AI Model Model Security; Governance, Risk and Compliance
ISO 42001 AI Coding and Orchestration Tools A.6 AI system life cycle; A.5 Assessing impacts of AI systems
AI Model A.6 AI system life cycle; A.10 Third-party and customer relationships; A.5 Assessing impacts of AI systems
Google SAIF AI Coding and Orchestration Tools Secure the AI supply chain; application and pipeline security; agent orchestration controls
AI Model Protect the AI model; ensure model integrity, provenance, and weight security
SANS Critical AI Security Guidelines AI Coding and Orchestration Tools Secure Agentic Systems and AI Autonomy Controls (defined function scope; execution isolation; API and function-call gating); Limit Model Behavior (focused functionality; access controls outside the model)
AI Model Conventional Security Controls (protect model parameters with least privilege, encryption at rest, runtime obfuscation, and trusted execution environments); Data/Model Engineering Controls (adversarial training; alignment and fine-tuning); AI Supply Chain Management (public-model caution; transfer-attack exposure)
MITRE ATLAS AI Coding and Orchestration Tools AML.T0051 LLM Prompt Injection; AML.T0054 LLM Jailbreak; AML.T0016 Obtain Capabilities (malicious plugins)
AI Model AML.T0043 Craft Adversarial Data; AML.T0024 Exfiltration via AI Inference API (subtechniques: AML.T0024.001 Invert AI Model and AML.T0024.002 Extract AI Model); AML.T0018 Manipulate AI Model (integrity and backdoor)
OWASP AI Exchange AI Coding and Orchestration Tools Development-time threats: agent framework supply chain; runtime threats: plugin abuse, prompt injection via tools
AI Model Development-time and runtime model threats: model inversion, extraction, evasion, poisoning
OWASP LLM Top 10 AI Coding and Orchestration Tools LLM01 Prompt Injection; LLM05 Improper Output Handling; LLM07 System Prompt Leakage; LLM10 Unbounded Consumption
AI Model LLM03 Supply Chain; LLM04 Data and Model Poisoning; LLM09 Misinformation
OWASP Agentic Security Top 10 AI Coding and Orchestration Tools ASI01 Agent Goal Hijack; ASI02 Tool Misuse and Exploitation; ASI05 Unexpected Code Execution (RCE); ASI07 Insecure Inter-Agent Communication; ASI08 Cascading Failures; ASI10 Rogue Agents
AI Model ASI04 Agentic Supply Chain Vulnerabilities (model provenance, weights, and dynamic loading)

Provenance

Last sourced 2026-07-17.

Expand Collapse

Sources

  1. KitOps GitHub repository
    Vendor source accessed 2026-06-24
  2. AI Supply Chain Security and Governance, Jozu
    Vendor source accessed 2026-09-22
    • “Models with critical CVEs, license conflicts, or missing signatures cannot deploy, eliminating the visibility and security gaps that cause production incidents.”
  3. Jozu homepage
    Vendor source accessed 2026-06-24
  4. Jozu Agent Guard page
    Vendor source accessed 2026-10-05
    • “Jozu Hub scans every model, agent, and MCP server across nine vulnerability classes before any of it runs, and attaches the results to the artifact itself as signed attestations”

Changelog

  1. Refreshed source citations and a coverage note.

  2. Refreshed source links and quotes against the current vendor pages.

  3. Updated a coverage note against the current vendor page.

  4. Refreshed a coverage source against the updated vendor page.

  5. Added to the catalog from the Jozu documentation.

Found an error? Corrections are welcome. Suggest an edit.