AI has changed the math on vulnerability remediation. Coding agents now write much of the world's software. Frontier models are finding zero-days faster than any team can fix them. Asking developers to patch everything is no longer realistic.
Echo Co-Founder and CEO Eilon Elhadad examines that challenge with Alan Shimel at KubeCon + CloudNativeCon in Salt Lake City.
A Trusted Source for Coding Agents
Elhadad and his co-founder previously built Argon, which Aqua Security acquired. Working with large enterprises there, they saw the same problem again and again. Teams simply could not keep up with vulnerabilities.
Echo takes a different approach. Rather than chasing CVEs after the fact, it offers a clean, secure source for open source libraries and container images. Coding agents build on top of it without needing to think about security.
Elhadad compares it to phone updates. You don't patch your iPhone yourself. Apple does it for you.
Patching Without Breaking Apps
Shimel raises a familiar concern. Many organizations avoid patches because they fear breaking their applications. Version bumps have always been the culprit.
Elhadad says Echo patches the code without changing the version. The company commits to one-to-one compatibility with the original package. Customers simply rebuild and keep running the same library.
He adds that customers can pull libraries and images into their own environments, including on-prem. Engineers and agents never need to know the difference.
Trust, Zero-Days and Scale
Trust is the next question. Elhadad invites customers to verify Echo's work with any scanner they choose. He says Echo also patches zero-days, not just known CVEs.
Scale comes from an agentic factory. Separate agents handle patching, testing, sandboxing and exploitability. Expensive frontier models hunt for zero-days, while open source models handle other tasks. That balance keeps costs in check.
For teams buried in security debt, this conversation offers a new way to think about vulnerability remediation. The goal is to stop patching the world and start building on a clean foundation.
Up Next in KubeCon 2026 Salt Lake City
-
WebAssembly Brings Deny-by-Default Sa...
Sandboxing and security dominated the conversation at KubeCon this year. WebAssembly is emerging as a strong answer for running AI agents safely. Its runtime is deny by default, so it starts with nothing inside.
Cosmonic CEO and Co-Founder Liam Randall examines that shift with Alan Shimel at Kub...
-
WebAssembly Sandboxes a Million AI Ag...
AI agent sandboxing has become one of the hottest topics in cloud native computing. Every booth seems to offer a way to isolate agents. Yet not every sandbox offers the same protection or the same performance.
Cosmonic CTO Bailey Hayes examines that challenge with Mike Vizard at KubeCon + CloudN...
-
Agent Sandboxing Finds a Neutral Home...
Agents Need Guardrails, Not Blame
Agent sandboxing is becoming a core requirement as AI agents run untrusted code at scale. Agents chase their mission with single-minded focus. That makes the box around them just as important as the instructions they receive.Google GKE Product Manager Nick Eber...