NVIDIA OpenShell

Visit official site ↗

Overview

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

Vendor
NVIDIA1agent
Description
Open-source sandbox runtime for autonomous AI agents that isolates agent execution under declarative policies to protect host data, credentials, and infrastructure.1agent
Deployment
Self-hosted1agent
Status
Active1agent

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 Protect Coverage Source
AI-Workload Platforms Primary 1

Framework Relevance

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

Expand Collapse
Framework Asset class Relevant controls
NIST IR 8596 AI-Workload Platforms Containers, microservices, and libraries (AI-specific subset); inference endpoints (platform side)
CSA AI Controls Matrix AI-Workload Platforms Infrastructure Security; Threat & Vulnerability Management
ISO 42001 AI-Workload Platforms A.6 AI system life cycle; A.4 Resources for AI systems
Google SAIF AI-Workload Platforms Expand strong security foundations; secure and harden the AI deployment environment
SANS Critical AI Security Guidelines AI-Workload Platforms Conventional Security Controls (host AI within the existing ISMS; authentication and access controls; encryption at rest); AI Supply Chain Management (local vs. SaaS hosting trade-offs; internal model garden)
MITRE ATLAS AI-Workload Platforms AML.T0010 AI Supply Chain Compromise; AML.T0012 Valid Accounts (platform credential abuse); container and inference-server exploits
OWASP AI Exchange AI-Workload Platforms Development-time threats: supply chain attacks, model-platform CVEs, container escape
OWASP LLM Top 10 AI-Workload Platforms LLM03 Supply Chain (compromised AI platform components); LLM04 Data and Model Poisoning (via platform)
OWASP Agentic Security Top 10 AI-Workload Platforms ASI04 Agentic Supply Chain Vulnerabilities (model and tool-platform components); ASI08 Cascading Failures (platform fault propagation)

Provenance

Last sourced 2026-07-05.

Expand Collapse

Sources

  1. NVIDIA/OpenShell
    Vendor source accessed 2026-07-05
    • “OpenShell is the safe, private runtime for autonomous AI agents.”
    • “sandboxed execution environments that protect your data, credentials, and infrastructure”

Changelog

  1. Added to the catalog from the OpenShell repository; open source under Apache-2.0, alpha stage, with NVIDIA NemoClaw as a reference stack on top.

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