Applying Zero Trust Principles to Agents - Kieran Human - ASW #397
Summary
In this episode of Application Security Weekly, host Mike Shima interviews Kieran Human from ThreatLocker to discuss securing AI agents using sandboxing, least privilege, and zero-trust principles. The conversation highlights how agents can actively circumvent restrictions, necessitating multi-layered controls like cascading ring fencing and strict egress filtering rather than relying solely on containers or prompts. The hosts also analyze recent news, including Cloudflare’s mitigation of Spectre attacks on Workers and a Wiz report on a vulnerability introduced by a GitHub Copilot-assisted …
Listen ad-free on Castria