As agentic AI systems transition from conceptual models to real-world deployments, MCP (Model Context Protocol) agents are emerging as a critical interface layer — and the next major attack vector. These autonomous, API-driven actors aren’t just executing tasks; they’re reshaping how LLMs interact with tools, data, and infrastructure across enterprise environments.
In this webinar, we’ll explore how MCP agents introduce unique security and trust challenges distinct from traditional LLM deployments and how to close these security gaps.
- A technical breakdown of the MCP architecture and its implications on security
- Emerging risks: from prompt and memory injection to cross-agent contamination
- Strategies for securing agent orchestration layers while preserving agent autonomy
If you’re building, deploying, or securing agentic systems, this discussion will surface new threat models and practical countermeasures for defending the rapidly evolving MCP layer.
SPEAKERS & BIOs
Ophir Dror, CPO & Co-Founder, Lasso Security
Ophir is a seasoned product and security leader, who led AI and strategy efforts for startups and enterprises. Ophir was the co-founder of a startup aiming to manage and visualize human interactions with generative AI products. In 2023, recognizing the need for GenAI adoption, he co-founded Lasso to address emerging challenges. Lasso offers a full GenAI Cyber Security suite to enable organizations to safely embrace the GenAI technology.
Or Oxenberg, Full Stack Data Scientist, Lasso Security
Or Oxenberg is a data scientist with a focus on machine learning and autonomous software systems. He currently brings his expertise to the security team at Lasso, where he contributes to advancing AI-driven defense technologies. He holds an M.Sc. in Information Systems Engineering with a strong foundation in graph and network theory algorithms, Or bridges deep academic insight with hands-on problem-solving to address complex challenges in data science.
Jason Ross, Product Security Principal, Salesforce.com
Jason Ross is a passionate cybersecurity expert with a diverse skill set in generative AI, Penetration Testing, Cloud Security, and OSINT. As a product security principal at Salesforce, Jason performs offensive security testing, with a specific focus on generative AI, Large Language Models, and Agentic systems. Jason is active in the security community, participating as a core member of the OWASP Top 10 for LLM Applications team, co-directing the information booth at BSides Las Vegas, serving as an NFO team member at DEFCON, and helping run the global CPTC event.
Akram Ageriff,
Akram Sheriff is a seasoned technologist and engineering leader with extensive experience in artificial intelligence (AI), machine learning (ML), generative AI (GenAI), Enterprise Networking and Internet of Things (IoT) systems. Currently, he serves as a Senior Software Engineering Manager within Cisco’s Outshift BU, where he focuses cutting edge innovation aligning to Agentic AI-driven networking, and edge computing. Akram is an active Technical member of OWASP, CSA, CoSAI, CNCF-AI , IOTG WG in IETF
