A deep dive on agent sandboxes
pierce.dev20 points by icyfox 9 hours ago
20 points by icyfox 9 hours ago
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.
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.
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.