OWASP Top 10 Agentic Applications
Details
The OWASP Top 10 for Agentic Applications 2026 is a globally peer-reviewed framework that identifies the most critical security risks facing autonomous and agentic AI systems. Developed through extensive collaboration with more than 100 industry experts, researchers, and practitioners, the list provides practical, actionable guidance to help organizations secure AI agents that plan, act, and make decisions across complex workflows.
Using an OWASP-centric Agentic Threat Emulator integrated with an Agentic SOC Range, we’ll demonstrate all ten risk categories:
ASI01 — Agent Goal Hijack
ASI02 — Tool Misuse & Exploitation
ASI03 — Identity & Privilege Abuse
ASI04 — Agentic Supply Chain Vulnerabilities
ASI05 — Unexpected Code Execution
ASI06 — Memory & Context Poisoning
ASI07 — Insecure Inter-Agent Communication
ASI08 — Cascading Failures
ASI09 — Human-Agent Trust Exploitation
ASI10 — Rogue Agents
For each scenario we’ll examine the vulnerable architecture, how the attack propagates through the agent workflow, what telemetry should be generated, and which engineering controls can stop it. We’ll work across: Agents LLM gateways RAG Memory MCP Tools Identity Policy Agent-to-Agent communication Human approvals.
The objective: understand how to build agentic systems that are observable, enforceable, and secure by design.
https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/
Presenter: Rod Soto
