Agentic AI Reference Architecture

Safety & Security · Data artifact

Sandbox Capability Test Suite

Data artifactSafety & SecuritySafety, Security & Governancearc:SandboxCapabilityTestSuite

A set of positive tests for permitted sandbox operations and negative tests for forbidden file, network, process and resource operations.

Responsibility. Specifies expected allow/block outcomes to confirm the sandbox is neither too restrictive nor too permissive.

is read bySandbox Validation Runner: is read bySandbox Validation Runner
Direct neighbourhood (hover for relationship types)

Relationships

is read by dependency

Sources

  1. Ch9.3: T. Nguyen, "Sandboxing and Transparency Foundations," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.3. ISBN: 9798244538229.