Skip to content
The El Paso

A flaw in three major AI agent platforms shows why guardrails don't work

A flaw in three major AI agent platforms shows why guardrails don't work
Photo: KVIA ABC-7 · view original

At Black Hat 2026, researchers Aviyam Ivgi and Hedi Ingber showed one structural flaw running through three of the largest agent stacks: AWS Bedrock AgentCore with the Strands SDK, Google’s Agent Development Kit, and Vercel’s AI SDK harness. They named that flaw CoreBreak. AWS patched CVE-2026-18...

Sources and story details