News for hackers. Stuff that matters.
Re:Cowork: Claude Code for the rest of your work by TeMPOraL on Monday January 12, 2026 @08:38PM (#46596430)
> In this case I think you would have to disallow any internet communication besides the LLM provider itself, including the underlying host of the sandbox.

And the user too, because a human can also be prompt-injected! Prompt injection is fundamentally just LLM flavor of social engineering.

There are no comments on this comment yet.