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

A business professional operating multiple AI agent platforms and system robots in an organization.

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-2026-18830 (CVSS 8.6), Google patched CVE-2026-18236 (CVSS 9.3, critical), and Vercel patched CVE-2026-64650 and CVE-2026-64651. All three vendors had put enforcement where the agent could reach it.

Originally published on redpanda.com, part of the BLOX Digital Content Exchange.

(0) comments

Welcome to the discussion.

Keep it Clean. Please avoid obscene, vulgar, lewd, racist or sexually-oriented language.
PLEASE TURN OFF YOUR CAPS LOCK.
Don't Threaten. Threats of harming another person will not be tolerated.
Be Truthful. Don't knowingly lie about anyone or anything.
Be Nice. No racism, sexism or any sort of -ism that is degrading to another person.
Be Proactive. Use the 'Report' link on each comment to let us know of abusive posts.
Share with Us. We'd love to hear eyewitness accounts, the history behind an article.