OWASP Top 10 for Agentic Applications 2026
Agentic Security Initiative, ASI01 to ASI10
The risk list for systems in which a model acts: goal hijack, tool misuse, identity and privilege abuse, supply chain, code execution, memory poisoning, inter-agent communication, cascading failures, trust exploitation and rogue agents.
Contribute
Spot an error, or know a record we should add? Members can propose additions and submit corrections.