~ / directory / aws-agentic-ai-security-matrix
AA
Mixed · AI Governance & Standards · reviewed 2026-04

AWS Agentic AI Security Matrix

AWS framework for scoping security requirements of autonomous AI systems.

01

What it does

An AWS-published framework for scoping security requirements of autonomous AI systems. Provides a matrix approach to mapping agent capabilities (tool use, memory, autonomy level) to appropriate security controls and governance requirements.

02

Security relevance

Authoritative guidance from a major cloud provider that provides a structured scoping methodology. Helps security teams answer 'how much security does this agent need?' based on its capabilities and access rather than applying one-size-fits-all controls.

03

When to use it

Use at the design phase of agentic AI projects to determine appropriate security controls. The concepts are transferable beyond AWS — the scoping methodology applies regardless of cloud provider. Accessible to non-specialists.

04

OWASP coverage

Risks addressed — mapped to both OWASP Top 10 standards. 2 in LLM, 10 in Agentic.

LLM Top 10 · 2025 · 2/10 covered
01
02
03
04
05
06
07
08
09
10
05

The raw record

What Yuntona stores. Single source of truth — fork it on GitHub.

name: AWS Agentic AI Security Matrix
slug: aws-agentic-ai-security-matrix
type: Mixed
category: AI Governance & Standards
url: https://aws.amazon.com/blogs/security/the-agentic-ai-security-scoping-matrix-a-framework-for-securing-autonomous-ai-systems

reviewed:   2026-04
added:      2026-04
updated:    2026-04

risks:
  llm:  [LLM07, LLM08]
  asi:  [ASI01, ASI02, ASI03, ASI04, ASI05, ASI06, ASI07, ASI08, ASI09, ASI10]

complexity:    Plug & Play
pricing:       —
audience:      All
lifecycle:     [scope]

tags: [Agentic, AWS, Framework, Reference]