Episode
AI Agents Don't Get New Keys. They Get Yours.
- Podcast
- Generative AI 101
- Published
- Aug 17, 2026
- Duration seconds
- 943
- Processing state
not_requested
Actions
POST https://stenobird.com/v1/public/podcasts/generative-ai-101-6932184/episodes/ai-agents-don-t-get-new-keys-they-get-yours/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/generative-ai-101-6932184/ai-agents-don-t-get-new-keys-they-get-yours.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
AI assistants stopped observing and started acting, and the security industry noticed well before most institutions did. Host Emily Laird tracks what changed when write access landed in enterprise connectors, why nearly a third of Black Hat's briefings targeted autonomous agents instead of base models, and how a trojanized skills package cleared 1.7 million downloads in under a month. Here's the part nobody puts on the vendor page: turning on an agent grants it no new permissions, it grants it yours, at machine speed, across every stale delegation and forgotten SharePoint site your organization has been quietly carrying since 2011. The tooling is early and the failure rates are high, but the permission audit is overdue regardless. 🎯 JOIN THE AI WEEKLY MEETUPS https://www.uwstout.edu/ai-weekly-meetup 📩 EMAIL REMINDERS FOR THE MEETUPS https://app.e2ma.net/app2/audience/signup/2101263/1779703/ 💬 CONNECT WITH EMILY LAIRD ON LINKEDIN http://www.linkedin.com/in/meet-emily-laird