Prateek Mishra
Cloud & Security Engineer | CKA | Speaker & Mentor
Lucknow, India
Actions
Prateek Mishra is a Cloud Engineer at Founda Health, building healthcare data platforms that run across cloud and on-prem using CNCF tech like Kubernetes, ArgoCD and OpenTelemetry, with security and privacy as the top priority.
Before that, he spent 5 years at Atlan, joining as an intern and leaving as an SDE-II, keeping multi-cloud systems secure at scale while helping it achieve SOC 2 Type II and ISO 27001 compliance.
These days he’s thinking about how to keep cloud systems secure by design as infrastructure gets more automated, and what access and trust should look like when AI agents are part of it.
Area of Expertise
Topics
Trust, but Sandbox: Securing AI Agents in Kubernetes
You wake up, open X, and see the post: new tool/model just dropped. By the time you finish your coffee, it’s installed, pointed at your repo, and already making “helpful” suggestions. It works. It feels safe. But what did you actually just hand over access to, and how would you even notice if it crossed a line?
In this talk, we’ll uncover why testing every new AI model or AI tool can quietly introduce serious security risks. Using real example inspired by incidents like OpenClaw, we’ll show how AI systems can access internal data, influence code paths, and create vulnerabilities without ever asking for permission.
We’ll discuss why experimentation without guardrails can bypass existing security controls and normalise unsafe patterns. Most importantly, focusing on what teams can do instead. The talk includes a live walkthrough using the Kubernetes agent-sandbox project to showcase how AI agents can be isolated, sandboxed, and constrained with clear boundaries.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top