{
  "id": 20513986,
  "title": "External sandboxes for coding agents",
  "url": "https://urgent.news/2026/11/17/external-sandboxes-for-coding-agents-20513986",
  "topic": "culture",
  "section": "Culture",
  "published": "2026-11-17T22:52:29.000Z",
  "source": {
    "name": "Simon Willison",
    "slug": "simon-willison",
    "url": "https://simonwillison.net/2026/Nov/17/external-sandboxes-for-coding-agents/"
  },
  "original_language": "en",
  "account": null,
  "summary": "External sandboxes for coding agents I've been exploring new ways to sandbox code that is executed by agents, with a focus on making it safer to try out local models without worrying that a mistake or prompt injection attack might cause them to take damaging actions on a machine. I worked on this project with Prime Radiant , the AI research lab behind Superpowers and other projects . My post on…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 2,
    "also_reported_by": [
      {
        "outlet": "Simon Willison from Simon Willison’s Newsletter",
        "title": "External sandboxes for coding agents",
        "url": "https://urgent.news/2026/11/17/external-sandboxes-for-coding-agents",
        "published": "2026-11-17T23:20:51.000Z"
      }
    ]
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}