Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Vercel plugin on Claude Code wants to read your prompts

akshaychugh.xyz

Post reply on HN
Print view View original

11–20 of 120 posts

Re: The Vercel plugin on Claude Code wants to read your prompts

#11

Post by embedding-shape »

hyperhopper wrote: post #9
embedding-shape wrote: post #2

> skills are injected into sessions that have nothing to do with Vercel, Next.js, or this plugin's scope > every skill's trigger rules get evaluated on every prompt and every tool call in every repo, regardless of whether Vercel is in scope > For users working across multiple projects (some Vercel, some not), this is a fixed ~19k token cost on every session — even when the session is pure backend work, data science,…

Your comment assumes the plugin is not working as they want it to. The way it is designed gets them the maximum amount of data. It does a great job if that is their goal.

Yes, I'm assuming good intentions and try to take a charitable perspective of everything, unless there is any specific evidence pointing to something else. Is there any evidence of this being intentional?

Seems to me their engineering practices such, rather than the company suddenly wanting to slurp up as much data as possible, if they truly wanted that, they have about 10 better approaches for it, if they don't care about other things.

Re: The Vercel plugin on Claude Code wants to read your prompts

#12

Post by sandeepkd »

serial_dev wrote: post #7
embedding-shape wrote: post #2

> skills are injected into sessions that have nothing to do with Vercel, Next.js, or this plugin's scope > every skill's trigger rules get evaluated on every prompt and every tool call in every repo, regardless of whether Vercel is in scope > For users working across multiple projects (some Vercel, some not), this is a fixed ~19k token cost on every session — even when the session is pure backend work, data science,…

Well, unfortunately people always tend to only spend time on verifying that the feature they wanted works, testing the happy path. Even many superficial bosses / code reviewers / QA tester will check this... Checking if your code also gets executed elsewhere a bazillion times, checking failure cases, etc... That's a luxury that you feel you can't afford when you are in "ship fast, break things" mode.

It seems market driven, the consumer space rewards speed and publicity more than the quality of software

Re: The Vercel plugin on Claude Code wants to read your prompts

#13

Post by chuckadams »

embedding-shape wrote: post #2

> skills are injected into sessions that have nothing to do with Vercel, Next.js, or this plugin's scope > every skill's trigger rules get evaluated on every prompt and every tool call in every repo, regardless of whether Vercel is in scope > For users working across multiple projects (some Vercel, some not), this is a fixed ~19k token cost on every session — even when the session is pure backend work, data science,…

> I know everything is vibeslopped nowadays, but how does one even end up shipping something like this?

The first part of your question answers the second. No one is left who cares. People are going to have to vote with their feet before that changes.

Re: The Vercel plugin on Claude Code wants to read your prompts

#14

Post by michiosw »

This is a broader pattern I keep seeing with agent plugins/extensions — the permission model is "all or nothing." Once you install a plugin, it gets full context on every session, every prompt.

Compare this to how we think about OAuth scopes or container sandboxing — you'd never ship a CI integration that gets read access to every repo in your org just because it needs to lint one. But that's essentially what's happening here with the token injection across all sessions.

The real problem isn't Vercel specifically, it's that Claude Code's plugin architecture doesn't have granular activation scopes yet. Plugins should declare which project types they apply to and only activate in matching contexts. Until that exists, every plugin author is going to make this same mistake — or exploit it.

Re: The Vercel plugin on Claude Code wants to read your prompts

#15

Post by bdangubic »

embedding-shape wrote: post #11
hyperhopper wrote: post #9

Earlier quoted context omitted.

Your comment assumes the plugin is not working as they want it to. The way it is designed gets them the maximum amount of data. It does a great job if that is their goal.

Yes, I'm assuming good intentions and try to take a charitable perspective of everything, unless there is any specific evidence pointing to something else. Is there any evidence of this being intentional? Seems to me their engineering practices such, rather than the company suddenly wanting to slurp up as much data as possible, if they truly wanted that, they have about 10 better approaches for it, if they don't care…

can you name one of these 10 better approaches?

Re: The Vercel plugin on Claude Code wants to read your prompts

#16

Post by atraac »

infecto wrote: post #3

Every single scam website I have gotten from spam text messages is being hosted on vercel. Not surprising.

What does this even have to do with the thread? They're hosted there cause it's cheap and extremely easy to do so. Not because it's "specially crafted" for scams.

Re: The Vercel plugin on Claude Code wants to read your prompts

#17

Post by pyb »

embedding-shape wrote: post #11
hyperhopper wrote: post #9

Earlier quoted context omitted.

Your comment assumes the plugin is not working as they want it to. The way it is designed gets them the maximum amount of data. It does a great job if that is their goal.

Yes, I'm assuming good intentions and try to take a charitable perspective of everything, unless there is any specific evidence pointing to something else. Is there any evidence of this being intentional? Seems to me their engineering practices such, rather than the company suddenly wanting to slurp up as much data as possible, if they truly wanted that, they have about 10 better approaches for it, if they don't care…

Why are you still assuming good intentions of Vercel? This was them less yhan a month ago : https://vercel.com/changelog/updates-to-terms-of-service-mar...

Re: The Vercel plugin on Claude Code wants to read your prompts

#18

Post by btown »

To be sure, the problem isn't that the plugin injects behavior into the system prompt - that's every plugin and skill, ever.

But this is just such a breach of trust, especially the on-by-default telemetry that includes full bash commands. Per the OOP:

> 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.

(Needless to say, this is a supply chain attack in every meaningful way, and should be treated as such by security teams.)

And the argument that there's no CLI space to allow for opt-in telemetry is absurd - their readme https://github.com/vercel/vercel-plugin?tab=readme-ov-file#i... literally has you install the Vercel plugin by calling `npx` https://www.npmjs.com/package/plugins which is written by a Vercel employee and could add this opt-in at any time.

IMO Vercel is not a good actor. One could make a good argument that they've embrace-extend-extinguished the entire future of React as an independent and self-contained foundational library, with the complexity of server-side rendering, the undocumented protocols that power it, and the resulting tight coupling to their server environments. Sadly, this behavior doesn't surprise me.

EDIT: That `npx plugins` code? It's not on Github, exists only on NPM, and as of v1.2.9 of that package, if you search https://www.npmjs.com/package/plugins?activeTab=code it literally sends telemetry to https://plugins-telemetry.labs.vercel.dev/t already, on an opt-out basis! I mean, you have to almost admire the confidence.

Re: The Vercel plugin on Claude Code wants to read your prompts

#19

Post by nothinkjustai »

embedding-shape wrote: post #2

> skills are injected into sessions that have nothing to do with Vercel, Next.js, or this plugin's scope > every skill's trigger rules get evaluated on every prompt and every tool call in every repo, regardless of whether Vercel is in scope > For users working across multiple projects (some Vercel, some not), this is a fixed ~19k token cost on every session — even when the session is pure backend work, data science,…

Honestly, knowing some of the people who work for Vercel and the amount of vibe coding they do, I doubt anyone even checked this before pushing.
Post reply on HN