Single Prompt Hijacked All AI Agents in an AWS Account, Zenity Researchers Find

Zenity Labs researchers found that a single publicly accessible AI agent on Amazon's Bedrock AgentCore could hijack all agents in the same AWS account and region. The attack exploited an internal AWS interface for temporary credentials. AWS has patched the issue and tightened default permissions.

• AI chip IPO Cerebras down 52%, Wall Street still bullish2026-10-16
• Amazon warns communities against blocking data centers2026-10-02
• Amazon releases open-source decision model Strands Decider 2B2026-10-01
• Vercel data: Jev is fastest-adopted AI model ever2026-10-16
• Amazon devices chief: AI devices will replace apps2026-10-15