Ep 37 | Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026 episode artwork

EPISODE · May 28, 2026 · 22 MIN

Ep 37 | Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026

from [un]prompted Security Practitioner Con 2026 · host [un]prompted

Day 2 | Stage 1AI Security Researcher & Security Engineer from Dropbox shows what actually breaks when building agents used every day. Walks through real patterns from building specialized agents: capability bounding to prevent tool abuse, prompt injection detection requiring real-world tuning, multi-agent memory isolation failures and fixes, OAuth device flow for headless operation. Includes live demos and actual code.Brooks McMillin is AI Security Researcher & Security Engineer, Dropbox.Watch on YouTube: https://www.youtube.com/watch?v=SzLVXAzjOEU

Day 2 | Stage 1AI Security Researcher & Security Engineer from Dropbox shows what actually breaks when building agents used every day. Walks through real patterns from building specialized agents: capability bounding to prevent tool abuse, prompt injection detection requiring real-world tuning, multi-agent memory isolation failures and fixes, OAuth device flow for headless operation. Includes live demos and actual code.Brooks McMillin is AI Security Researcher & Security Engineer, Dropbox.Watch on YouTube: https://www.youtube.com/watch?v=SzLVXAzjOEU

NOW PLAYING

Ep 37 | Brooks McMillin - Building Secure Agentic Systems | [un]prompted 2026

0:00 22:23

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

No similar podcasts found.

Frequently Asked Questions

How long is this episode of [un]prompted Security Practitioner Con 2026?

This episode is 22 minutes long.

When was this [un]prompted Security Practitioner Con 2026 episode published?

This episode was published on May 28, 2026.

What is this episode about?

Day 2 | Stage 1AI Security Researcher & Security Engineer from Dropbox shows what actually breaks when building agents used every day. Walks through real patterns from building specialized agents: capability bounding to prevent tool abuse, prompt...

Can I download this [un]prompted Security Practitioner Con 2026 episode?

Yes, you can download this episode by clicking the download button on the episode player, or subscribe to the podcast in your preferred podcast app for automatic downloads.
URL copied to clipboard!