We strolled through an enterprise AI assistant's backend, helped ourselves to full application takeover and access to every chat log, and had a Microsoft Entra ID dump for dessert — no prompt injection, no model tricks, no AI expertise required.
  • halfdane@piefed.socialEnglish
    0·
    12 hours ago

    Seems like you’re talking about a different article: there was no context-poisoning, or in fact even anything LLM specific in this attack.