做智能体应用开发的团队终于有了一个默认安全的沙箱方案——Perplexity 把密钥管理、内容检测、数据加密和存储计算分离都做了，建议直接参考他们的设计思路。
Perplexity 正在构建市场上最安全的可扩展智能体运行时沙箱。其安全设计包括：安全处理代理 API 密钥、对所有智能体访问的内容进行安全检测、加密通过连接器传递给智能体的数据、以及可靠地分离存储和计算。Perplexity Computer 默认安全，每个任务在独立的硬件隔离沙箱中运行，具有 VPC 级别的存储和计算分离。智能体通过短期代理令牌进行身份验证，而不是使用原始 API 密钥。
Perplexity is building one of the most secure scalable agent runtime sandboxes in the market right n...
Perplexity is building one of the most secure scalable agent runtime sandboxes in the market right now. A blog post on how we: 1. Handle proxy API keys for agents securely 2. Run safety detection for all content accessed by agents 3. Encrypt data passed via connectors to agents 4. Decouple storage and compute reliably Perplexity @perplexity_ai Computer is secure by default. Every task runs in its own hardware-isolated sandbox with VPC-level storage and compute separation. Agents are authenticated with short-lived proxy tokens instead of raw API keys. 🔗 View Quoted Tweet 💬 30 🔄 27 ❤️ 350 👀 35645 📊 63 ⚡