alt Hacker NewsThe point is that auto mode gives people a false sense of security that leads them to believe they don't need to run Claude in a proper sandbox. This same attack running in a sandbox (even in YOLO mode) would be comparatively harmless.
Replies
bombcar • today at 11:55 AM
Auto mode is for people who just keep hitting "YES" on everything, it's a bit better than that.
But it's real easy to give auto mode instructions (like "always ask before deploy") and then bypass that just normally.
➕ show 2 replies
rcxdude • today at 12:33 PM
I also feel like this is an attack that manual review is not that likely to catch, given none of the malicious code appears in any of the tool calls or output.
Can you suggest a proper sandbox on mac? One that allows both me and the agent to interact with the processes? Where it can drive browser, for both oauth setup and runtime visual inspection? I've tried building docker setups, but can't figure out the browser driving part.