OWASP Top 10 For AgenticApplications 2026

Agentic AI systems are moving quickly from pilots to production across finance, healthcare, defense, critical infrastructure, and the public sector. Unlike task-specific automations, agents plan, decide, and act across multiple steps and systems, often on behalf of users and teams. The Agentic Security Initiative has already begun defining safeguards for Agentic applications but publishing a set of guidelines spanning across the lifecycle.

Our core taxonomy (Agentic AI – Threats and Mitigations) provides a baseline definition of agents, their
relationship to LLM applications, the role of autonomy, and a detailed treatment of threats and mitigations. Additional documents cover Threat Modelling (Agentic Threat Modelling Guide), Securing architecture, design, development, and deployment of Agentic apps (Securing Agentic Applications), as well as governance (State of Agentic AI Security and Governance).

These publications provide a comprehensive set of guidelines intended as a reference and an in-depth
cover. Nevertheless, their breadth can make them difficult to translate into day-to-day practice for builders, defenders, and decision-makers.

Our OWASP Top 10 for Agentic Applications (or OWASP Agentic Top 10) serves as a compass and go-to
reference for security leaders and practitioners to understand and address the Top 10 highest-impact
threats and begin their journey.