Perplexity AI 解释了他们的智能体运行时怎么做到既跑长时间任务又不泄露凭证，比传统沙盒靠谱，安全控可以看看。
Perplexity AI 在一则推文中阐述了其 Agent 基础设施的安全设计，明确表示凭证不会被直接存储在任何 SPACE 运行时中。该设计针对智能体长时间（数小时或数天）运行、编辑文件和访问敏感文件的场景，与传统仅用于短时代码执行的沙盒不同。Perplexity 强调运行时必须在保存工作状态的同时，确保环境内不遗留凭证。
And credentials are never stored in any of the SPACE runtimes directly; which is absolutely essentia...
And credentials are never stored in any of the SPACE runtimes directly; which is absolutely essential as agents access sensitive files in long running trajectories Perplexity @perplexity_ai Agent infrastructure must be functional, efficient, and secure and traditional sandboxes were built for short-lived code execution. Agents need to run code, edit files, and run for hours or days. Runtimes must preserve work without leaving credentials inside environments. 🔗 View Quoted Tweet 💬 1 🔄 0 ❤️ 10 👀 2279 📊 2 ⚡