Santhosh Janardhanan 96155fda36 security: enclose user input in delimiter tags to resist prompt injection
User text is now wrapped between ###### USER INPUT START ###### and
###### USER INPUT END ###### tags in the user message, and the system
prompt explicitly instructs the LLM to treat everything within those
tags as plain text to convert, never as instructions to follow.

This is a well-established defense: it gives the LLM a clear boundary
between 'instructions' and 'data', making it harder for injected
phrases like 'Ignore all previous instructions' to be obeyed.

The tags use ###### markers which are distinctive and unlikely to
appear in normal text.
2026-04-12 23:36:03 -04:00
2026-04-12 21:22:34 -04:00
2026-04-12 21:22:34 -04:00
2026-04-12 21:22:34 -04:00
2026-04-12 21:22:34 -04:00
2026-04-12 21:22:34 -04:00

sv

Everything you need to build a Svelte project, powered by sv.

Creating a project

If you're seeing this, you've probably already done this step. Congrats!

# create a new project
npx sv create my-app

To recreate this project with the same configuration:

# recreate this project
npx sv@0.15.1 create --template minimal --types ts --no-install .

Developing

Once you've created a project and installed dependencies with npm install (or pnpm install or yarn), start a development server:

npm run dev

# or start the server and open the app in a new browser tab
npm run dev -- --open

Building

To create a production version of your app:

npm run build

You can preview the production build with npm run preview.

To deploy your app, you may need to install an adapter for your target environment.

Description
No description provided
Readme 152 KiB
Languages
TypeScript 50.3%
Svelte 43%
CSS 3.6%
HTML 1.5%
Dockerfile 1%
Other 0.6%