prompt-injector
AI
prompt injection testing
SHOW HN2025
prompt-injector
A minimal TS library that generates prompt injection attacks
prompt-injector.blueprintlab.ioHow HN took it
0 positive, 2 neutral or asking, 0 mixed, 4 critical, out of 6 comments about the project. Thread score -0.38.
Execution: 0 for, 2 againstDocs: 0 for, 1 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Maker openly admitted the vibe-coded nature and committed to fixing issues
From 2 comments
There's absolutely no problem with not knowing what you're doing! Just, you know, own it. Part of what I find exhausting about projects like this is I can't see any evidence of…
mpalmer on HNyes absolutely, updating the page now as we speak!
yaoke259 on HN
Objections
Website and README claims (25+ patterns, 100+ patterns, integrations) are unsupported and sources not linked
From 1 comment
The website copy is obviously generated, and has not been reviewed for correctness. The website trumpets "25+ curated prompt injection patterns from leading security research".…
mpalmer on HN
Usage instructions missing; the library is hard to find in the repo
From 2 comments
Was the whole lib and website vibe coded? I can't find any instructions on how to use it, the repo is for the website itself and the readme is AI blurb that doesn't make me any…
sippeangelo on HNThe project appears to be located inside the repo of the website: https://github.com/BlueprintLabIO/prompt-injector/tree/main/src/lib
HKayn on HN
Content appears AI-generated and unreviewed
From 2 comments
Was the whole lib and website vibe coded? I can't find any instructions on how to use it, the repo is for the website itself and the readme is AI blurb that doesn't make me any…
sippeangelo on HNThe website copy is obviously generated, and has not been reviewed for correctness. The website trumpets "25+ curated prompt injection patterns from leading security research".…
mpalmer on HN
SvelteKit is heavy for a single-page site
From 1 comment
Why did you use something as heavy as SvelteKit for a website with a single page? This doesn't inspire confidence.
HKayn on HN
Requests
Link the research sources and verify citations
From 1 comment
The website copy is obviously generated, and has not been reviewed for correctness. The website trumpets "25+ curated prompt injection patterns from leading security research".…
mpalmer on HN
Add a clear personal voice and disclose vibe-coding
From 1 comment
There's absolutely no problem with not knowing what you're doing! Just, you know, own it. Part of what I find exhausting about projects like this is I can't see any evidence of…
mpalmer on HN
Questions
What are good prevention mechanisms for prompt injection?
From 1 comment
What are some good prevention mechanisms for this? A sort of firewall for prompts? I've seen people recommend LLMs, but that seems like it wouldn't work well. What is the…
mosselman on HN