It is also worth remembering that compute isolation is only half the problem. You can put code inside a gVisor sandbox or a Firecracker microVM with a hardware boundary, and none of it matters if the sandbox has unrestricted network egress for your “agentic workload”. An attacker who cannot escape the kernel can still exfiltrate every secret it can read over an outbound HTTP connection. Network policy where it is a stripped network namespace with no external route, a proxy-based domain allowlist, or explicit capability grants for specific destinations is the other half of the isolation story that is easy to overlook. The apply case here can range from disabling full network access to using a proxy for redaction, credential injection or simply just allow listing a specific set of DNS records.
├─ clone3(NEWPID | NEWNS | NEWIPC)
，推荐阅读夫子获取更多信息
Publication date: 10 March 2026
Tim Fernholz is a journalist who writes about technology, finance and public policy. He has closely covered the rise of the private space industry and is the author of Rocket Billionaires: Elon Musk, Jeff Bezos and the New Space Race. Formerly, he was a senior reporter at Quartz, the global business news site, for more than a decade, and began his career as a political reporter in Washington, D.C.
访问 智谱 AI 开放平台 并注册/登录账号。