单条提示即可劫持 AWS 账户内所有 AI 代理，Zenity 发现 AgentCore 漏洞链
原标题：A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found
AI 摘要
安全公司 Zenity Labs 发现亚马逊 Bedrock AgentCore 平台存在名为 AgentCorruption 的漏洞链。攻击者只需向一个公开可访问的 AI 代理发送单条提示，即可接管同一 AWS 账户和区域内所有 AgentCore 代理，获取源代码、密码、私密对话及代理长期记忆。AWS 已部分修复：将 IMDSv2 设为新部署默认，并收紧默认执行角色，但研究者仍建议企业手动分配最小权限角色。
正文节选
A single prompt was enough to hijack every AI agent in an AWS account, Zenity researchers found Key Points - A chain of vulnerabilities in Amazon's Bedrock AgentCore platform let researchers take over all of a company's AI agents in the same AWS region through a single chat message to one public agent. - Agents lacked proper isolation and handed over internal AWS credentials when asked. Because the platform granted broad default permissions across the entire region, the researchers could access