Dropbox 如何利用 MCP 和 Dash 弥合设计到代码的安全鸿沟

Every security team knows the drill: a new feature goes through design review, a threat model is produced, mitigations are agreed upon, and then development begins. In many cases, by the time implementation reaches code review, the process where engineers review code changes before they go live, the original security requirements are no longer visible in the workflow. A threat model, which outlines potential security risks and the protections a feature should include, often lives in a separate document or system from the code itself.

每个安全团队都熟悉这个流程：新功能经过设计审查，生成威胁模型，商定缓解措施，然后开始开发。在许多情况下，当实现进入代码审查（即工程师在代码上线前审查代码更改的过程）时，最初的安全要求在流程中已不再可见。威胁模型概述了潜在的安全风险以及功能应包含的保护措施，它通常存在于与代码本身分离的单独文档或系统中。

This separation creates a challenge. Implementation often happens weeks or months after the original security review, making it difficult for reviewers to verify that the agreed-upon security requirements were actually implemented. At Dropbox, we wanted to understand how often this gap appears in practice.

这种分离带来了一个挑战。实施通常发生在原始安全审查的几周或几个月后，这使得审查人员很难验证商定的安全要求是否真正得到了实施。在 Dropbox，我们希望了解这种差距在实际中出现的频率。

That led us to build a system that combines three technologies: Model Context Protocol, foundational large language models (which we’ll refer to as foundational models), and Dash, the AI capabilities within Dropbox that make it easier to find and understand your team’s content. Together, these technologies automatically retrieve relevant threat models during code review and evaluate whether code changes align with the requirements defined in them. Because Dash already indexes and connects content stored in Dropbox and across our connected applications, the system can draw on years of security reviews and engineering documentation without requiring teams to manually link those sources together.

这促使我们构建了一个结合三种技术的系统：Model Context Protocol、基础大语言模型（我们将其简称为基础模型）以及 Dash，Dash 是 Dropbox 内部的 AI 功能，可让您更轻松地查找和理解团队的内容。这些技术共同作用，在代码审查期间自动检索相关的威胁模型，并评估代码更改是否符合其中定义的要求。由于 Dash 已经对存储在 Dropbox 中以及跨我们连接的应用程序的内容进行索引和连接，该系统可以利用多年的安全审查和工程文档，而无需团队手动将这些来源链接在一起。

In t...