InfoNewsLLM-specific
External sandboxes for coding agents
- Published
- Record updated
Summary
Simon Willison, working with Prime Radiant, describes an external sandbox pattern in which code run by a coding agent executes inside a separate sandbox while the agent itself stays outside it. Three sandbox server implementations are released, external-sandbox-v86, external-sandbox-container and external-sandbox-quicksand, each exposing the same localhost API that Pi, Claude Code or Codex can call. The sandboxes also offer an optional HTTP/HTTPS allow-list proxy and a credential replacement mechanism so the agent can make authenticated calls without holding the secret.
Topics
Related items
- HighCVE-2026-75612: yt-mcp arbitrary file read through add_attachment file_pathSimilar attack · NVD/CVE Database
- HighCVE-2026-130121: The AI Puffer - MCP Server for Claude & ChatGPT, with AI Chatbot plugin for WordPress is vulnerable to Stored…Similar attack · NVD/CVE Database
- InfoEvolution Under Fire: Evolving Agent Safety Harnesses with Adaptive Injection StressorsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- InfoConfGuard: a physics-grounded reference monitor for predictive-maintenance large-language-model agentsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
- MediumCVE-2026-130358: AdminNeo before 5.9.1 contains a missing authentication vulnerability in the ClaudeSqlPlugin, GeminiSqlPlugin, and…Similar attack · NVD/CVE Database