{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/1e4ce025ea4749fab169195e7b1222ba\" frameborder=\"0\" width=\"1658\" height=\"1243\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1243,"width":1658,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1243,"thumbnail_width":1658,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/6c3bf74a99124ac69bd9210ee436f23f-766cd14745a62773-full.jpg","duration":297.995,"title":"DEMO ONLY","description":"In this video, I discuss the significant security concerns surrounding AI adoption, particularly prompt injections that can compromise user data. I explain how our HackAgent team stress tests AI agents to ensure their robustness against these vulnerabilities. We’ve recently deployed a new package that allows users to monitor attacks through our API dashboard. I encourage you to explore our demo and see how our tools can help secure your AI projects."}