[simonw]

I'm more excited about this than I was about MCP.

MCP was conceptually quite complicated, and a pretty big lift in terms of implementation for both servers and clients.

Skills are conceptially trivial, and implementing them is easy... provided you have a full Linux-style sandbox environment up and running already. That's a big dependency but it's also an astonishingly powerful way to use LLMs based on my past 6 months of exploration.

[carlgreene]

I’m curious some of the things you’re having the LLM/agents do with a full Linux sandbox that you wouldn’t allow on your local machine

[simonw]

I remain afraid of prompt injection. If I'm telling Claude Code to retrieve data from issues in public repos there's a risk someone might have left a comment that causes it to steal API keys or delete files or similar.

I'm also worried about Claude Code making a mistake and doing something like deleting stuff that I didn't want deleted from folders outside of my direct project.

[ajtejankar]

With so many code sandbox providers coming out I would go further than you say that this is almost a non-problem.