Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A deep dive on agent sandboxes

pierce.dev

Post reply on HN
Print view View original

1–10 of 22 posts

Re: A deep dive on agent sandboxes

#2

Post by pama »

I would like to see more articles about agent sandboxes. With agents gaining popularity we need a higher fraction of users to understand containers and sandboxes and their risk profiles, and then to communicate their understandings to friends and family. It is a harder task than explaining ChatGPT, and it often feels like a hindrance.

Re: A deep dive on agent sandboxes

#3

Post by ashishb »

6 months back I started dockerizing my setup after multiple npm vulnerabilities.

Then I wrote a small tool[1] to streamline my sandboxing.

Now, I run agents inside it for keeping my non-working-directory files safe.

For some tools like markdown linter, I run them without network access as well.

1- https://github.com/ashishb/amazing-sandbox

Re: A deep dive on agent sandboxes

#4

Post by nullishdomain »

ashishb wrote: post #3

6 months back I started dockerizing my setup after multiple npm vulnerabilities. Then I wrote a small tool[1] to streamline my sandboxing. Now, I run agents inside it for keeping my non-working-directory files safe. For some tools like markdown linter, I run them without network access as well. 1- https://github.com/ashishb/amazing-sandbox

This looks awesome! Do you have a mental process you run through to determine what gets run in the sandbox, or is it your default mode for all tools?

Re: A deep dive on agent sandboxes

#5

Post by ashishb »

nullishdomain wrote: post #4
ashishb wrote: post #3

6 months back I started dockerizing my setup after multiple npm vulnerabilities. Then I wrote a small tool[1] to streamline my sandboxing. Now, I run agents inside it for keeping my non-working-directory files safe. For some tools like markdown linter, I run them without network access as well. 1- https://github.com/ashishb/amazing-sandbox

This looks awesome! Do you have a mental process you run through to determine what gets run in the sandbox, or is it your default mode for all tools?

> This looks awesome! Do you have a mental process you run through to determine what gets run in the sandbox, or is it your default mode for all tools?

Here's what I use it for right now

- yarn - npm - pnpm - mdl - Ruby-based Markdown linter - fastlane - Ruby-based mobile app release tool by Google - Claude Code - Gemini CLI

Over time, my goal is to run all CLI-based tools that only need access to the current directory (and not parent directories) via this.

Re: A deep dive on agent sandboxes

#8

Post by bigwheels »

zmj wrote: post #7

devcontainers, devcontainers, devcontainers

Totally, devcontainers are fantastic! In this agent sandboxing space there's also Leash, which in addition to Docker/Orbstack/Podman provides a sophisticated macOS-native system extension mode - https://github.com/strongdm/leash

Re: A deep dive on agent sandboxes

#10

Post by linolevan »

The secret proxy trick is something I expect to become standard at some point in the near future. I first saw this trick being used in Deno Sandboxes (https://docs.deno.com/sandboxes/security/) but it's cheap/easy to implement so I'd be surprised if this doesn't become the standard for a lot of these BaaS platforms.
Post reply on HN