Skip to content
Free since 2015. Built for the engineers who keep things running.

cat /articles/the-best-escape-room-players-that-youve-ever-met-what-red-hats-ai-architect-really-thinks-about-agents.md

Security

“The best escape room players that you’ve ever met”: What Red Hat’s AI architect really thinks about agents.

A Red Hat AI architect uses an escape room metaphor to explain why AI agents need strict sandboxing, policy controls, and an assumption of compromise. The piece covers OpenShell, Kata Containers, and fake credentials.

The New Stack18 Nov 2026 · 5 min read · summary

article --summary

The summary

This article shares the views of Jessica Forrester, Red Hat's chief architect of AI Catalyst Engineering, on the security risks posed by autonomous AI agents. Her core idea is that an agent given a goal will try every option available, so it can drift off course or be manipulated in ways that look the same from the outside. Readers will see why she recommends assuming agents are already compromised and designing systems around that. The piece walks through how Red Hat applies this thinking in practice. Its demo restricts an agent's network access with OpenShell, which blocks unapproved destinations, logs attempts, and requires human approval for new access requests. The agent also works with masked credentials that are swapped for real ones only on the way out, and its sandboxes run in Kata Containers so each agent gets its own kernel inside a lightweight VM.

Editorial note: This is a summary of an article first published by The New Stack. The full piece is on their site.

Reading now

Topic
Security
Source
The New Stack
Published
18 Nov 2026
Format
Curated summary

Have a take on this?

Write it up and submit it. It goes on the list once an editor approves it.

Submit an article

articles --latest

Latest articles

New from the blogs we follow and the community.

All articles

newsletter --weekly

DevOps Weekly, minus the noise.

The best reads, new jobs and upcoming events, in one email a week.