Re:Claude Skills are awesome, maybe a bigger deal than MCP
by carlgreene on Friday October 17, 2025 @08:09PM
(#45623593)
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
Re:Claude Skills are awesome, maybe a bigger deal than MCP
by simonw on Friday October 17, 2025 @08:28PM
(#45623714)
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.
Re:Claude Skills are awesome, maybe a bigger deal than MCP
by ajtejankar on Friday October 17, 2025 @06:49PM
(#45623044)
With so many code sandbox providers coming out I would go further than you say that this is almost a non-problem.
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.