The Agentic Threats Navigator is a guide that outlines key attack surfaces in agentic AI systems, including reasoning, memory, tools, identity, human oversight, and multi-agent interactions. It provides threats and examples to help security teams understand and assess risks in agentic AI systems.
OWASP Gen AI Security Project – Agentic Threats Navigator Read Post »
This paper examines the practical implications of large language models (LLMs) in offensive cybersecurity, moving beyond theoretical possibilities to assess their real-world effectiveness. The research, conducted by the CTI Layer Team at OWASP Top Ten For LLMs, explores the ability of LLMs such as GPT-4o, Claude, and DeepSeek r-1 to exploit vulnerabilities in the OWASP
OWASP LLM Exploit Generation v1.0 Read Post »
Agentic AI represents an advancement in autonomous systems, increasingly enabled by large language models (LLMs) and generative AI. While agentic AI predates modern LLMs, their integration with generative AI has significantly expanded their scale, capabilities, and associated risks. This document is the first in a series of guides from the OWASP Agentic Security Initiative (ASI)
Agentic AI – Threats and Mitigations Read Post »
The rapid proliferation of Large Language Models (LLMs) across various industries has highlighted the critical need for advanced data security practices. As these AI systems become more sophisticated, they bring with them unprecedented risks, including potential breaches of sensitive information and challenges in meeting stringent data protection regulations. This white paper outlines a comprehensive set
LLM and Gen AI Data Security Best Practices Read Post »
This guide outlines the critical components of GenAI Red Teaming, with actionable insights for cybersecurity professionals, AI/ML engineers, Red Team practitioners, risk managers, adversarial attack researchers, CISOs, architecture teams, and business leaders. The guide emphasizes a holistic approach to Red Teaming in four areas: model evaluation, implementation testing, infrastructure assessment, and runtime behavior analysis.
GenAI Red Teaming Guide Read Post »
Updated for Q1, 2025 – The LLM and Generative AI Security Solutions Landscape is tailored for a diverse audience comprising developers, AppSec professionals, DevSecOps and MLSecOps teams, data engineers, data scientists, CISOs, and security leaders who are focused on developing strategies to secure Large Language Models (LLMs) and Generative AI applications. It provides a reference
LLM and Generative AI Security Solutions Landscape – Q1,2025 Read Post »
Excerpted from the AI Security Solutions Landscape guide for Q1, 2025, This includes the LLM & Gen AI Security Solutions Cheat Sheet as well as the Cheat Sheet for outlining the LLM and Gen AI Sec Ops, stages and actions.
Download the full document at https://genai.owasp.org/ai-security-solutions-landscape/
AI Security Solution Cheat Sheet Q1-2025 Read Post »
The OWASP Top 10 for Large Language Model Applications started in 2023 as a community-driven effort to highlight and address security issues specific to AI applications. Since then, the technology has continued to spread across industries and applications, and so have the associated risks. As LLMs are embedded more deeply in everything from customer interactions to internal operations, developers and security professionals are discovering new vulnerabilities—and ways to counter them.
OWASP Top 10 for LLM Applications 2025 Read Post »
The LLM and Generative AI Security Solutions Landscape is tailored for a diverse audience comprising developers, AppSec professionals, DevSecOps and MLSecOps teams, data engineers, data scientists, CISOs, and security leaders who are focused on developing strategies to secure Large Language Models (LLMs) and Generative AI applications. It provides a reference guide of the solutions available
LLM and Generative AI Security Solutions Landscape Read Post »
As generative AI technologies evolve and integrate into various aspects of business and society, the need for robust governance, security, and policy management becomes paramount. Establishing a Center of Excellence (COE) for Generative AI Security aims to bring together diverse groups such as security, legal, data science, operations, and end-users to foster collaboration, develop best
LLM and Generative AI Security Center of Excellence Guide Read Post »
warranty of service or accuracy. For more information, please refer to our General Disclaimer. – Copyright © 2025 OWASP Foundation, Inc.