How-toOfficial

Skyflow 与 Amazon Bedrock AgentCore Gateway 保护智能体工具调用数据安全

Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway

Why we picked it

做智能体开发的朋友可以看看:AWS 的 AgentCore Gateway 现在能挂 Skyflow 拦截器,敏感数据先换 token 再传给工具和模型,授权方才能还原,而且一行 agent 代码都不用改。要过 PCI、GDPR 合规的团队值得照着这个模式搭一套。

AWS 与 Skyflow 联合发布了在 Amazon Bedrock AgentCore Gateway 中保护智能体工具调用数据的方法。核心做法是将 Skyflow 作为 Gateway 的 interceptor(拦截器),在数据到达任何工具、模型或日志之前完成去标识化处理。

Image · AWS Machine Learning Blog
Body

具体机制上,Skyflow 拦截器会把敏感数据(如身份证号、银行卡号等)替换为 token 后再传给下游工具和模型,授权调用方请求时再由 Skyflow 还原为真实数据。整个过程对智能体代码零侵入,开发者不需要修改现有的 agent 逻辑,只需在 Gateway 层配置拦截器即可。

这套方案解决的痛点是:智能体调用外部工具时,敏感数据往往会被写入模型上下文、工具日志或第三方系统,造成合规风险。对需要同时满足 PCI、GDPR 等合规要求的企业开发者来说,这是在 AgentCore Gateway 体系内可以直接落地的一种数据脱敏模式。

Original · AWS Machine Learning Blog

Protect agent tool calls with Skyflow and Amazon Bedrock AgentCore Gateway

Learn how Skyflow and Amazon Bedrock AgentCore Gateway keep sensitive data out of the tools your AI agents call. Added as a gateway interceptor, Skyflow de-identifies data before any tool, model, or log sees it, and restores it for authorized callers, with no change to your agent code.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "How-to" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Amazon Bedrock, AgentCore Gateway, Skyflow, agents.

Primary source verification: published directly by AWS Machine Learning Blog with first-party authority.