| ▲ | jdkoeck 3 hours ago |
| But even then, the agent can still exfiltrate anything from the sandbox, using curl. Sandboxing is not enough when you deal with agents that can run arbitrary commands. |
|
| ▲ | TheDong 2 hours ago | parent | next [-] |
| It depends on what you're trying to prevent. If your fear is exfiltration of your browser sessions and your computer joining a botnet, or accidental deletion of your data, then a sandbox helps. If your fear is the llm exfiltrating code you gave it access to then a sandbox is not enough. I'm personally more worried about the former. |
| |
| ▲ | jdkoeck 2 hours ago | parent [-] | | Code is not the only thing the agent could exfiltrate, what about API keys for instance? I agree sandboxing for security in depth is good, but it’s not sufficient and can lull you into a false sense of security. | | |
| ▲ | twodave an hour ago | parent [-] | | This is what emulators and separate accounts are for. Ideally you can use an emulator and never let the container know about an API key. At worst you can use a dedicated account/key for dev that is isolated from your prod account. | | |
| ▲ | gessha 8 minutes ago | parent [-] | | VM + dedicated key with quotas should get you 95% there if you want to experiment around. Waiting is also an option, so much of the workflow changes with months passing so you’re not missing much. |
|
|
|
|
| ▲ | philipp-gayret 2 hours ago | parent | prev [-] |
| That depends on how you configure or implement your sandbox. If you let it have internet access as part of the sandbox, then yes, but that is your own choice. |
| |
| ▲ | jdkoeck an hour ago | parent [-] | | Internet access is required to install third party packages, so given the choice almost no one would disable it for a coding agent sandbox. In practice, it seems to me that the sandbox is only good enough to limit file system access to a certain project, everything else (code or secret exfiltration, installing vulnerable packages, adding prompt injection attacks for others to run) is game if you’re in YOLO mode like pi here. Maybe a finer grained approach based on capabilities would help: https://simonwillison.net/2025/Apr/11/camel/ |
|