AWS 发布 Strands Box 智能体沙箱

1. 01:42
   网页The Register· Discussion

   AWS launches open-source AI agent sandbox to prevent YOLO mode disasters(opens the original post in a new tab)
2. 01:36
   AWS SecuritySelected

   AWS releases Strands Box: an AI agent sandbox based on Dogwood policies

   AWS released the open-source sandbox Strands Box as a developer preview under the Apache 2.0 license, combining OS-level isolation with fine-grained policies to constrain AI agent behavior. The Box embeds the previously open-sourced policy language Dogwood and its local evaluation engine, making allow or deny decisions at multiple execution points including network egress, the Python interpreter, the Shell interpreter, and the MCP server proxy, with execution points sharing event history so rules can depend on the agent's prior actions. For example, a policy can limit the agent to sending at most 3 messages to Slack every 10 minutes, returning HTTP 403 with the rule ID and description when denied. The Box is configured via two files, box.toml and policy.dw; the egress gateway can inject real credentials on the agent's behalf, with the agent only receiving placeholder tokens.

1. Time not given
   Strands Agents

   AWS 开源 Strands Box 本地沙箱，用 Dogwood 语义策略约束 AI 智能体

   AWS 发布开源本地沙箱 Strands Box 开发者预览版，将操作系统隔离与 Dogwood 语义策略结合，用于约束 AI 智能体的行为。Box 采用内核级隔离机制，但把策略层放在用户空间，让所有系统与工具交互只能经由策略层，从而对 MCP 调用、shell 与 Python 程序、文件系统和网络访问实施策略。策略可按工具粒度确定性执行，例如要求 git push 前必须通过 npm test，或限制某智能体每天调用支付 API 不超过 100 美元、每小时调用 AWS MCP 服务器不超过 60 次。Box 不绑定特定模型或框架，可与任意智能体框架配合使用。作者也指出该方案需要信任更多代码，包括解释器和协议拦截器，建议云端多租户部署时配合每会话独立 MicroVM，例如运行在 AgentCore Runtime 内。

Current attention48·Peak in the comparable period57（Oct 8 10:00）·Change over the comparable past 24 hours 0%