OWASP® Foundation

So much collaboration, learning, and idea sharing at the OWASP Contributor Workshop in Oslo! 🙌 Huge thanks to all the speakers and attendees who showed up ready to share knowledge, collaborate, and build together. This is what the OWASP community is all about. #owasp #opensource #appsec #community

We released version 1.13.1 of #OWASP #WrongSecrets! Now with #springboot4 and challenges involving #telegram #AI, #MCP . You can test it at https://lnkd.in/e_EHfsJ2 . Like what you see? Please give our repo https://lnkd.in/ejYfwmrt a 🌟 if you like it! #security #opensource

How do you deploy LLMs in the enterprise without creating a security nightmare? Organizations everywhere are experimenting with Large Language Models and generative AI to increase productivity and automate workflows. But along with the opportunity comes real risk: prompt injection, data exfiltration, insecure outputs, and the growing problem of shadow AI inside organizations. On March 18, we’ll be hosting a virtual session exploring what it takes to deploy LLMs securely in an enterprise environment. Our speaker,Aaron Ansari, brings more than 20 years of application security experience from organizations including BMW Group and Trend Micro. Aaron also served 13 years as Co-Chapter Chair of OWASP Central Ohio and has spent 18+ years teaching programming and secure coding in Python at Franklin University. In this session, Aaron will walk through the architecture and security controls required for real-world LLM deployments, including: • Understanding the modern LLM threat landscape, including prompt injection and training data poisoning • Designing safer AI systems using Retrieval-Augmented Generation (RAG) • Implementing governance and access control for vector databases • Applying layered security controls across the entire AI stack Whether you’re experimenting with generative AI or already integrating LLMs into production systems, this session will provide a practical security framework for building AI systems that are both powerful and responsible. 📅 March 18 💻 Virtual Event Register here: https://luma.com/owaspla Special thanks to our event sponsor: https://lnkd.in/gbwMb8E8 We look forward to seeing the community there.

Happy Friday, folks! 🚀 Missed a session or want to relive the best moments from OWASP Global AppSec DC? The talk recordings are now live on YouTube. 🎥 Catch the sessions you missed 🔁 Share your favourites 💡 Keep the AppSec learning going Press play and start your weekend with some security inspiration. Happy Friday, folks! 🚀 Missed a session or want to relive the best moments from OWASP Global AppSec DC? The talk recordings are now live on YouTube. 🎥 Catch the sessions you missed 🔁 Share your favourites 💡 Keep the AppSec learning going Press play and start your weekend with some security inspiration. https://lnkd.in/eTYGBQjZ #owasp #appsec #infosec #opensource #cybersecurity

What a fantastic night at the OWASP Mixer in Oslo after NDC Security! 🍻 Beer, tapas, great conversations, and of course, a lively group game of Cornucopia to top it all off. Huge thanks to our friends at Aikido Security for sponsoring the evening and being part of the fun! 🙌 #owasp #appsec #infosec #community #ndc #oslo #cornucopia

Had a fantastic conversation today with Rob van der Veer as part of our AI Vulnerability Webinar Series discussing the role of the OWASP AI Exchange in securing agentic AI systems. We’re entering a world where AI systems don’t just answer questions, they plan, decide, access tools, and execute actions. In many ways, we’ve given AI systems the keys to the building… before installing the locks. A few key insights from the discussion: 🔹 The biggest risk isn’t just prompt injection, it’s how agents interact with tools and the real world. 🔹 Cross-user indirect prompt injection is an emerging threat many organizations are still underestimating. 🔹 The biggest security win today? Blast radius control through least privilege, oversight, and transparency. 🔹 Security teams must be willing to “spoil the party” with risk analysis before innovation turns into incident response. What gives hope? Collaboration. Seeing organizations like SANS Institute and OWASP AI Exchange align on shared controls is exactly the kind of signal the industry needs. Because securing agentic AI isn’t a tooling problem. It’s a guidance, architecture, and community problem and the work is just getting started. #AIsecurity #AgenticAI #OWASP #OWASPAIExchange hashtag #AISecurity #CyberSecurity #LLMSecurity #AIgovernance #PromptInjection #AISafety #AppSec #SecurityCommunity

Looking for vulnerable web apps to play with? You need to look at the OWASP Vulnerable Web Applications Directory, especially as it has a new home: https://vwad.owasp.org/  Feedback appreciated! #owasp #appsec

Day one at NDC Security in Oslo was a brilliant start,great conversations, plenty of learning, and of course lots of swag for the sticker collectors out there! We’re ready to do it all over again tomorrow. Who’s joining us for the OWASP mixer? https://luma.com/txn0myuk