Articles tagged with "ai-agent"
A real-world MCP permission bypass shows why Kubernetes/K3s clusters need disciplined RBAC design and audit-log separation before letting AI agents operate them.
Handing AI agents static API keys is an operating model that eventually breaks down. This article explains why static secrets hit a wall when running MCP servers on Kubernetes, and how Keycloak combined with SPIFFE/SPIRE enables a 'keyless' authentication design.
Code generated and executed by AI agents can no longer be treated as a trusted, reviewed product. This article explains the limits of container isolation and why Kata Containers' microVM isolation is becoming essential when designing AI agent sandboxes on Kubernetes.