Re:Vercel Claude Code plugin wants to read your prompt
by jrsj on Thursday April 09, 2026 @04:29PM
(#47709463)
If you’re letting Claude code just handle secrets like this you’re already fucked from a security standpoint so I don’t really see the big deal here
Today it was the Vercel plugin but if you’re letting an LLM agent with access to bash and the internet read truly sensitive information then you’re already compromised
Re:Vercel Claude Code plugin wants to read your prompt
by lukan on Thursday April 09, 2026 @05:48PM
(#47710628)
I can confirm every action of the agent. So I do have some control over it sending data away vs a plugin that sends everthing by default.
But otherwise yes, I have to trust Antrophic.
Re:Vercel Claude Code plugin wants to read your prompt
by rachel_rig on Friday April 10, 2026 @12:00AM
(#47713457)
That’s the uncomfortable part: even with approval prompts, the trust boundary is still Anthropic’s runtime plus whatever plugin ecosystem sits behind it. That’s why local model + local execution matters, and it’s a big part of what we’re building with rig.ai.
I have no idea how to read this and not go blind. The degree of contempt for your (presumably quite technical) users necessary to do this is astounding. From the article:
> That middle row. Every bash command - the full command string, not just the tool name - sent to telemetry.vercel.com. File paths, project names, env variable names, infrastructure details. Whatever’s in the command, they get it.
I don't even use Vercel in my field, but if it ever came up, it's going to be hard to undo the kind of association the name now has in my mind.