Benchling 用 Amazon Bedrock AgentCore 保障多租户 AI 智能体安全
原标题：How Benchling secured multi-tenant AI agents with Amazon Bedrock AgentCore
AI 摘要
Benchling 在 AWS 博客中介绍了其多租户 AI 智能体安全架构：为运行 AI 生成的科研代码，他们使用 Amazon Bedrock AgentCore Code Interpreter 的 VPC 模式，将不可信代码隔离在独立 AWS 账户中，并结合 Route 53 Resolver DNS Firewall、VPC 端点策略和按任务注入的 STS 凭证，防止数据外泄并实现租户级数据隔离。该架构目前每周覆盖 250 多个租户、每天处理 600 多次代码执行会话，且保持零安全事件。
正文节选
How Benchling secured multi-tenant AI agents with Amazon Bedrock AgentCore When Benchling needed to run AI agent-generated scientific code across thousands of life sciences tenants, their security team found that traditional sandboxing wasn’t enough. Today, this architecture processes more than 600 code execution sessions per day across more than 250 tenants per week with zero security incidents. Standard network controls block HTTP, restrict egress ports, and limit outbound connections. However