AI Security Research Portal
methodactiveMethods

Threat Modeling Agentic Systems

Purpose

Model actors, authority, tools, memory, retrieval, delegated actions, identity propagation, and failure recovery as first-class attack surfaces.

Evidence Base

Representative Sources

TitleKindDateTagsRaw
MITRE ATLASwhitepaperunknownMITRE, adversarial-ai, ai-security, mitre-atlas, tactics-techniques, threat-modelingraw
AI Snitches Get Glitches: Towards Evading Agentic Surveillancepaper2026-06-24adversarial, agentic-ai, ai-security, monitoring, surveillance-evasionraw
AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systemspaper2026-06-20agentic-ai, ai-security, governance, risk-management, sbomraw
AWS Security Agent adds threat modeling, Kiro power and Claude Code plugin, and moreofficial_blog2026-06-17ai-for-security, code-review, coding-agents, mcp, security-agent, strideraw
TrustedARI: Towards Trust-Native Agentic Routing Infrastructure for Agentic AIpaper2026-06-14agentic-ai, ai-security, multi-agent-systems, routing, trust-infrastructureraw
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systpaper2026-06-03Liya Su, Suchen Liu, Tianyun Liu, Tingwen Liu, Yingjie Zhang, Yuanbo Xieraw
State of Agentic AI Security and Governance 2.01official_whitepaper2026-06-01OWASP Gen AI Security Project, agentic-ai, governance, owasp, security-for-ai, standardsraw
Careful Adoption of Agentic AI Servicesofficial_guidance2026-04-30ASD's ACSC, CISA, Canadian Centre for Cyber Security, NCSC-NZ, NCSC-UK, NSAraw

Use In This Portal

Apply this method when ingesting sources, evaluating claims, or answering research questions that need evidence discipline rather than narrative summary.