Agentic AI threat modeling: are your runtime controls keeping up?

TL;DR: AI threat modeling for agentic systems must account for prompt injection, unsafe tool use, poisoned retrieval data, excessive agency, and unauthorized access to sensitive systems because behaviour changes at runtime, according to Lasso Security. The practical shift is from static architecture review to continuous modelling of identity, permissions, trust boundaries, and tool-use paths before agents become embedded in business workflows.

NHIMG editorial — based on content published by Lasso Security: How to Build an AI Threat Modeling Process for Agentic Systems

Questions worth separating out

Q: How should security teams apply threat modeling to AI systems?

A: Security teams should model AI systems as a combination of data pipelines, inference surfaces, outputs, and connected workflows.

Q: Why do AI agents create more governance risk than ordinary integrations?

A: AI agents can connect quickly, run continuously, and accumulate broad permissions across multiple services.

Q: What breaks when AI agents are given broad inherited permissions?

A: Broad inherited permissions break the assumption that access is tied to a narrow business need.

Practitioner guidance

• Inventory every agent, tool, and MCP connection Build a complete register of GenAI applications, orchestration layers, memory stores, and connected business systems.
• Map trust boundaries and runtime decision points Document where prompts, retrieved content, tool outputs, and downstream actions cross from untrusted to privileged contexts.
• Constrain agent permissions to task scope Assign the minimum access needed for each workflow and separate read, write, and action privileges wherever possible.

What's in the full article

Lasso Security's full blog post covers the operational detail this post intentionally leaves for the source:

• Step-by-step guidance for inventorying agents, MCP connections, and orchestration layers across live environments.
• Framework-by-framework mapping that shows how to combine MAESTRO, MITRE ATLAS, and NIST AI RMF in practice.
• Control examples for runtime enforcement, deviation detection, and approval gating across agent workflows.
• Threat pattern breakdowns for prompt injection, tool poisoning, and poisoned retrieval that are not fully expanded here.

👉 Read Lasso Security's guide to building an AI threat modelling process for agentic systems →

Agentic AI threat modeling: are your runtime controls keeping up?

Explore further

View Full Forum →  |  NHI Foundation Course →