- GEN AI SECURITY
- Getting Started
- Resources
Resources Library
Get the latest on the Top 10 for LLMs and Generative AI application security developments from OWASP and InfoSec publications. Discover how leaders in tech are leveraging the projects resources to build trustworthy and secure generative AI applications.
Subscribe with RSS to keep up with the latest from the community.
OWASP GenAI Security Project – Solutions Reference Guide Q2_Q3’25
The OWASP GenAI Security Project – Solutions Reference Guide (Q2–Q3 2025) is a comprehensive, vendor-agnostic resource for organizations seeking to secure Large Language Models (LLMs) and Agentic AI applications. It extends the OWASP Top 10
CheatSheet – A Practical Guide for Securely Using Third-Party MCP Servers 1.0
The Practical Guide for Securely Using Third-Party MCP Servers from the OWASP GenAI Security Project provides a detailed framework for safely deploying and managing external Model Context Protocol (MCP) servers. It outlines the unique security
OWASP GenAI Security Project Threat Defense COMPASS 1.0
The OWASP GenAI Security Project’s Threat Defense COMPASS consolidates AI threats, vulnerabilities, defenses, and mitigations into a unified AI Threat Resilience Strategy Dashboard. COMPASS enables organizations to evaluate everything from external adversaries using AI tools
OWASP GenAI Security Project – Threat Defense COMPASS RunBook
The OWASP GenAI Security Project’s Threat Defense COMPASS consolidates AI threats, vulnerabilities, defenses, and mitigations into a unified AI Threat Resilience Strategy Dashboard. COMPASS enables organizations to evaluate everything from external adversaries using AI tools
Al Security Solutions Landscape For LLM and Gen Al Apps Q2/Q3 2025
The Solutions Landscape monitors and maps the full LLM and Generative AI lifecycle, focusing on the DevOps–SecOps intersection to meet evolving security needs. Guided by the OWASP Top 10 Risks and Mitigations for LLM and
FinBot Agentic AI Capture The Flag (CTF) Application
FinBot is part of the OWASP GenAI Security Project’s Agentic Security Initiative, created to equip builders and defenders with hands-on tools for understanding and mitigating agentic AI risks. FinBot is an Agentic Security Capture The
AI Security Solutions Landscape for Agentic AI Q3 2025
The Solutions Landscape monitors and maps the full Agentic AI lifecycle, focusing on the DevOps–SecOps intersection to meet evolving security needs. Guided by the Agentic AI Threats and Mitigations guide and SecOps tasks, it highlights
OWASP Gen AI – Agentic Security Top 10 Global Kickoff Presentation
The OWASP Gen AI Security Project – Agentic Security Initiative, brought together community members, experts and contributors virtually and in 4 location around the globe (London, Las Vegas – Black Hat, Athens, and TelAviv to
State of Agentic AI Security and Governance 1.0
The State of Agentic AI Security and Governance provides a comprehensive view of today’s landscape for securing and governing autonomous AI systems. It explores the frameworks, governance models, and global regulatory standards shaping responsible Agentic
GenAI Incident Response Guide 1.0
The OWASP GenAI Security Project commissioned this GenAI Incident Response guide to help fill this need by providing security practitioners with guidelines and best practices for how to respond to security incidents involving GenAI applications.
Securing Agentic Applications Guide 1.0
This guide aims to provide practical and actionable guidance for designing, developing, and deploying secure agentic applications powered by large language models (LLMs). It complements the OWASP Agentic AI Threats and Mitigations (ASI T&M) document
大規模言語モデル（LLM）アプリケーションに関するOWASP Top 10
大規模言語モデル（LLM）アプリケーションに関するOWASP Top 10は、AIアプリケーション特有のセキュリティ問題を浮き彫りにし、対処するためのコミュニティ主導の取り組みとして2023年に開始されました。それ以来、この技術はさまざまな業界やアプリケーションに広がり続け、それに伴うリスクも増大しています。LLMが顧客とのやり取りから社内業務に至るまで、あらゆるものに深く組み込まれるにつれて、開発者やセキュリティ専門家は新たな脆弱性を発見し、その対策案に貢献しています。
2025 में LLM Applications के लि ए OWASP के शी र्ष 10
बड़े भाषा मॉडल अनुप्रयोगों के लिए OWASP शीर्ष 10 2023 में AI अनुप्रयोगों के लिए विशिष्ट सुरक्षा मुद्दों को उजागर करने और संबोधित करने के लिए एक समुदाय-संचालित प्रयास के रूप में शुरू हुआ। तब
OWASP Τοπ-10 για Εφαρμογές LLM 2025
Το OWASP Τοπ-10 για Εφαρμογές Μεγάλων Γλωσσικών Μοντέλων (LLM) ξεκίνησε το 2023 ως πρωτοβουλία της κοινότητας με στόχο να επισημάνει και να αντιμετωπίσει ζητήματα ασφάλειας ειδικά για εφαρμογές ΤΝ. Έκτοτε, η τεχνολογία εξαπλώθηκε σε πλήθος
LLM 애플리케이션을 위한 OWASP Top 10 2025
LLM 애플리케이션을 위한 OWASP Top 10은 2023년 AI 애플리케이션 관련 보안 문제를 해결하기 위한 커뮤니티 주도의 노력으로 시작되었습니다. 그로부터 이 기술은 산업과 애플리케이션 전반에 걸쳐 계속 확산되어 왔으며 관련 위험도 함께 증가하였습니다. 고객과의 상호 작용부터
Agent Name Service (ANS) for Secure Al Agent Discovery v1.0
The Agent Name Service (ANS), developed under the OWASP GenAI Security Project – Agentic Security Initiative, introduces a secure, DNS-inspired framework for AI agent discovery. ANS leverages Public Key Infrastructure (PKI) for identity verification, structured
Multi-Agentic system Threat Modeling Guide v1.0
This guide builds on the OWASP Agentic AI – Threats and Mitigations publication, our master agentic threat taxonomy, by applying its threat taxonomy to real-world multi-agent systems (MAS). These systems, characterized by multiple autonomous agents
Insecure Agent Samples
GenAI Project – Agentic Security Initiative (ASI) – Insecure Agent Samples Warning The sample applications here are deliberately insecure to demonstrate Agent security risks. Please exercise caution when deploying in your environment. Objective
OWASP Top 10 для LLM и генеративного ИИ (2025)
Это обновление — актуальный и всеобъемлющий ресурс, который охватывает клю��евые риски, уязвимости и методы их устранения для защиты генеративного ИИ и LLM-приложений на всех этапах их жизненного цикла: разработки, развертывания и управления. Независимо от того,
OWASP Top 10 para Aplicações de LLM e IA Generativa (2025)
Esta atualização oferece um recurso abrangente e atualizado que aborda os principais riscos, vulnerabilidades e medidas de proteção para garantir a segurança das aplicações de IA Generativa e LLMs em todo o seu ciclo de
