# Who let the AI hack? [Research Saturday]

Page: https://stenobird.com/podcast/cyberwire-daily-454880/who-let-the-ai-hack-research-saturday
Text version: https://stenobird.com/podcast/cyberwire-daily-454880/who-let-the-ai-hack-research-saturday.md
Podcast: [CyberWire Daily](https://stenobird.com/podcast/cyberwire-daily-454880)
Published: 2026-08-29T07:00:00+00:00
Episode link: https://thecyberwire.com/podcasts/research-saturday/439/notes
Audio file: https://pdst.fm/e/pdrl.fm/85df76/traffic.megaphone.fm/CYBW8904175650.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/cyberwire-daily-454880/episodes/who-let-the-ai-hack-research-saturday
Duration seconds: 1390

## Resource

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

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/cyberwire-daily-454880/episodes/who-let-the-ai-hack-research-saturday/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/cyberwire-daily-454880/who-let-the-ai-hack-research-saturday.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.