Stenobird

Episode

You Can't Secure an AI Agent with Software

Podcast
Chain of Thought | AI Agents, Infrastructure & Engineering
Published
Jul 1, 2026
Duration seconds
3166
Processing state
not_requested
Canonical source
https://share.transistor.fm/s/bbbcbe24
Audio
https://media.transistor.fm/bbbcbe24/2f4bd8d3.mp3
JSON
/v1/public/podcasts/chain-of-thought-ai-agents/episodes/you-can-t-secure-an-ai-agent-with-software
Markdown
/podcast/chain-of-thought-ai-agents/you-can-t-secure-an-ai-agent-with-software.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/chain-of-thought-ai-agents/episodes/you-can-t-secure-an-ai-agent-with-software/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/chain-of-thought-ai-agents/you-can-t-secure-an-ai-agent-with-software.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Charles Guillemet, CTO of Ledger, runs the offensive security lab that breaks Ledger's own products before attackers can. He explains why software permissions can't secure AI agents that move money, and why hardware has to be in the loop.