{"podcast":{"title":"CyberWire Daily","slug":"cyberwire-daily-454880","podcast_index_feed_id":454880,"rss_url":"https://feeds.megaphone.fm/cyberwire-daily-podcast","website_url":"https://thecyberwire.com/podcasts/daily-podcast","image_url":"https://megaphone.imgix.net/podcasts/58ab7ae0-def8-11ea-b34c-b35b208b0539/image/8676ed612d7a335a98a9173d70cb11be.png?ixlib=rails-4.3.1&max-w=3000&max-h=3000&fit=crop&auto=format,compress","author":"N2K Networks, Inc.","episode_count":3765,"summary":"The daily cybersecurity news and analysis industry leaders depend on. Published each weekday, the program also includes interviews with a wide spectrum of experts from industry, academia, and research organizations all over the world.","last_synced_at":"2026-09-23T20:18:19.501651+00:00","page_url":"https://stenobird.com/podcast/cyberwire-daily-454880"},"episode":{"title":"Who let the AI hack? [Research Saturday]","slug":"who-let-the-ai-hack-research-saturday","published_at":"2026-08-29T07:00:00+00:00","page_url":"https://stenobird.com/podcast/cyberwire-daily-454880/who-let-the-ai-hack-research-saturday","show_page_url":"https://stenobird.com/podcast/cyberwire-daily-454880","url":"https://thecyberwire.com/podcasts/research-saturday/439/notes","audio_url":"https://pdst.fm/e/pdrl.fm/85df76/traffic.megaphone.fm/CYBW8904175650.mp3","summary":"Today we are joined by Crystal Morin, Senior Cybersecurity Strategist, and Michael Clark, Senior Director of Threat Research, at Sysdig, sharing their work on \"LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools.\" The Sysdig Threat Research Team observed an attacker abusing an exposed, unauthenticated Ollama server as the “brain” for an automated offensive security tool. The AI-powered framework can fingerprint services, identify vulnerabilities, craft exploits, extract credentials, and orchestrate attacks toward command execution, with researchers capturing the tool while it was still under active development. The activity highlights how LLMjacking is evolving from simply stealing AI compute for profit into using stolen model capacity to build increasingly autonomous offensive capabilities. The research and executive brief can be found here: LLMjacking evolved: Attackers are using stolen AI compute to build offensive agentic tools Learn more about your ad choices. Visit megaphone.fm/adchoices","meta_description":"Today we are joined by Crystal Morin, Senior Cybersecurity Strategist, and Michael Clark, Senior Director of Threat Research, at Sysdig, sharing their wor…","key_points":[],"chapters":[],"topics":[],"duration_seconds":1390,"processing_state":"not_requested","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/cyberwire-daily-454880/episodes/who-let-the-ai-hack-research-saturday/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/cyberwire-daily-454880/who-let-the-ai-hack-research-saturday.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}