LodeHQ
AI news for people who shipFree, by email

AI · simonwillison.net · Wednesday, 18 November 2026

External sandboxes let coding agents run risky code away from your machine

Coding agents can now execute code inside a separate sandbox while the agent itself stays outside it, making local-model experiments safer against mistakes and prompt injection attacks. The project offers three servers using WebAssembly, Apple Containers, or Microsoft’s Quicksand library, all with the same localhost API for Pi, Claude Code, and Codex. An optional allow-list proxy controls network access, while credential replacement enables authenticated calls without exposing secrets to the agent.

Read the source: simonwillison.net ↗In the 18 November issue →