AI Matters
Why it matters
Security flaw allowed complete takeover of AWS AI agents
The Decoder A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found
Security researchers at Zenity Labs discovered a vulnerability in Amazon's Bedrock AgentCore that allowed a single prompt to hijack all agents in an AWS account.
Why it matters
Companies building cloud-based AI agents must secure internal interfaces, as a single prompt could have compromised entire cloud accounts.
Latest brief · Oct 19, 2026