Posts

If there was one message emanating from day two of RSAC 2026, it was this: agentic AI security is no longer a niche concern. It’s the defining enterprise security challenge of 2026, and the industry is mobilizing fast. From CrowdStrike’s new runtime protection tools to Palo Alto Networks’ Prisma AIRS 3.0 and a wave of vendors rethinking what “identity” means in a world of autonomous digital workers, Day 2 of the conference made clear that the security industry is finally taking AI agents seriously. ...

Anthropic just made “vibe coding” a lot less nerve-wracking — and a lot more autonomous. The company launched auto mode for Claude Code, now in research preview, giving the AI itself the authority to decide which permissions it needs when executing tasks. It’s a significant philosophical shift: instead of developers choosing between micromanaging every action or recklessly enabling --dangerously-skip-permissions, the model now makes those judgment calls. What Auto Mode Actually Does Auto mode is essentially a smarter, safety-wrapped evolution of Claude Code’s existing dangerously-skip-permissions flag. Before this change, that flag handed all decision-making to the AI with no safety net — any file write, any bash command, no questions asked. That was powerful but obviously risky. ...

Agentic AI workloads just became a formal conformance concern in the cloud-native world. At KubeCon + CloudNativeCon Europe 2026 in Amsterdam, CNCF announced a significant update to its Kubernetes AI Conformance Program — nearly doubling the number of certified AI platforms and, more importantly, adding agentic workflow validation to the conformance test suite. This is the cloud-native ecosystem’s official acknowledgment that AI agents are no longer experimental workloads. They’re production infrastructure that needs to be validated like everything else. ...

Most AI agent frameworks are built to work. Dapr Agents is built to survive. That’s the core pitch behind the Dapr Agents v1.0 general availability announcement, made by the Cloud Native Computing Foundation (CNCF) at KubeCon + CloudNativeCon Europe 2026 in Amsterdam on March 23rd. While the rest of the agentic AI ecosystem debates which LLM to use and which reasoning framework is smarter, Dapr Agents has been solving a quieter but arguably more fundamental problem: what happens to your agent when the Kubernetes node it’s running on dies? ...

OpenAI shipped ChatGPT Library — a persistent file storage system that survives across conversations — and most coverage has treated it as a quality-of-life feature. You can finally keep your documents without re-uploading them. Convenient! But there’s a more interesting way to read this announcement, and it’s the one that matters for anyone tracking how AI agents are evolving: this is memory infrastructure, and it’s the foundation that makes persistent agents possible at scale. ...

If you’re running OpenClaw and haven’t updated recently, stop what you’re doing and check your version. A newly disclosed vulnerability — CVE-2026-32895 — allows an attacker with basic access to bypass the authorization controls that keep your Slack DM allowlists and per-channel user restrictions intact. The fix is in version 2026.2.26 and later. If you’re not there, you’re exposed. What’s Vulnerable The flaw lives in OpenClaw’s system event handlers for two subtypes: member and message. These handlers process events like message_changed, message_deleted, and thread_broadcast — normal Slack plumbing that OpenClaw routes and acts on. ...

One of the persistent frustrations with AI agents in production is that nobody agrees on how to know if they’re working correctly. Solo.io is taking a shot at solving that with agentevals, an open-source project launched at KubeCon + CloudNativeCon Europe 2026 in Amsterdam. The premise is straightforward but the execution is non-trivial: continuously score your agents’ behavior against defined benchmarks, using your existing observability data, across any LLM model or framework. Not a one-time evaluation. Not a test suite that only runs before deployment. A live, ongoing signal. ...

There’s a spectrum of trust you can give a coding agent. At one end: you approve every file write and bash command manually, one by one. At the other end: you run --dangerously-skip-permissions and let the AI do whatever it judges necessary. Both extremes have obvious problems — the first is slow enough to defeat the purpose, the second is a security incident waiting to happen. Anthropic’s new auto mode for Claude Code is an attempt to find a principled middle ground — not by letting humans define every permission boundary, but by letting the AI classify its own actions in real time and deciding which ones are safe to take autonomously. ...

When CNCF updates its conformance certification program, it’s not just updating a checklist — it’s defining what the cloud-native community considers a first-class production concern. The announcement at KubeCon Europe 2026: agentic workloads are now a first-class production concern. CNCF announced an update to the Kubernetes AI Conformance Program that nearly doubles the number of certified AI platforms and, more significantly, adds agentic workflow validation to the conformance testing suite. ...

The software supply chain attack models your security team has been defending against for the past decade assumed one thing: the entities making decisions inside your build pipeline were humans. Slow, reviewable, occasionally careless humans — but humans. Coding agents like Claude Code, Cursor, and GitHub Copilot Workspace have changed that assumption. They are autonomous participants in the software development lifecycle: generating code, selecting dependencies, executing build steps, and pushing changes at machine speed. The attack surface they introduce is the natural consequence of giving a privileged, autonomous system access to an environment where a single bad decision can propagate into production before any human review process catches it. ...