AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

External sandboxes for coding agents

2026-11-17
unverified public report Unknown Unknown

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 the Prime Radiant blog introduces the external sandbox pattern, where code executed by the agent runs inside a dedicated sandbox while the agent itself lives outside of that sandbox. To demonstrate this pattern we've released three sandbox server implementations: external-sandbox-v86 runs a Node.js server which then uses v86 to run Alpine Linux inside WebAssembly. external-sandbox-container is a Python web server which runs the sandbox in Alpine Linux inside an Apple Containers instance. external-sandbox-quicksand is another Python web server, this time using Microsoft's Quicksand sandboxing lib

Risk rationale: model (+5), prompt injection (+20) Source: simonwillison.net ↗
TECHNIQUESTA0042 Jailbreak / Prompt Injection
43Risk
24Confidence

← All incident reports