How to Fix the Security Flaw Built Into Every AI Agent | The Ledger Podcast ft. Shisa.ai
Get every episode summarized
Each time The Ledger Podcast publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
About this episode
AI agents are capable and easily fooled at the same time. They can read your data, act on your behalf, and reach the outside world. Because LLMs don't fundamentally separate data from instructions, anything they read can be treated as a command.
In this episode of The Ledger Podcast, Leonard Lin, CTO of Shisa.ai, in conversation with Ledger Chief Human Agency Officer Ian Rogers, talks about building AI agents you can trust. Leonard's framework, Shisa D, inverts the usual control plane so the AI proposes and the system decides. Secrets are removed from the model, tool calls are reviewed by a separate layer, and the highest-risk actions route to a Ledger signer, where you see the real intent in plain text and approve it with a physical tap.
Plus a live demo of Shisa D routing an action to a Ledger signer for hardware approval.
Hosted on Acast. See acast.com/privacy for more information.
Get every episode summarized
Each time The Ledger Podcast publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
Hosts & guests
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from The Ledger Podcast
AI Made Security Flaws Cheap to Find. What Now?
The Ledger Podcast
How AI Agents Get Paid on Solana Without Touching Private Keys
The Ledger Podcast
Inside DeFi Vaults: Staying in Control of Your Assets
The Ledger Podcast
Quantum Is Not Here Yet. The Trust Problem Is.
The Ledger Podcast