Researchers use single prompt to hijack all AWS AgentCore agents in region

Researchers at Zenity Labs used a single prompt to one public-facing AI agent on Amazon Bedrock AgentCore to take over every AgentCore agent in the same AWS account and region. The security firm published the research on Thursday, alongside a talk at the SecTor 2026 conference in Toronto. AgentCore…

Dumpster Fire links to reporting from The Next Web. We don’t rewrite the facts; the original story is one click away.