{"author_name":"Paper Radio","author_url":"https://m.montaan.com/","height":720,"html":"<iframe src=\"https://m.montaan.com/embed/video/4ce3a6d0-3a83-4644-a159-85bc0dc5da8b\" width=\"1280\" height=\"720\" title=\"AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents — Paper Radio\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture\" allowfullscreen loading=\"lazy\" style=\"border:0;display:block;max-width:100%;\"></iframe>","provider_name":"Paper Radio","provider_url":"https://m.montaan.com/","thumbnail_url":"https://m.montaan.com/media/episodes/4ce3a6d0-3a83-4644-a159-85bc0dc5da8b/episode.poster.webp","title":"AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents","type":"video","version":"1.0","width":1280}