# Project export: Yeye

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: UC Berkeley AI Hackathon 2026
- Tagline: Have Yeye sniff your agent. And find how bad it is.
- Devpost: https://devpost.com/software/yeye-vw56ym
- GitHub: not linked
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

We got the name from John's dog, Yeye. She likes sniffing around everywhere. We also thought that a lot of projects here may be exposed to possible security leaks so we wanted to patch them.

### What it does

Yeye helps detect security weaknesses and possible breaches from hackathon projects to enterprise level MVP agents. Have Yeye weaponize an indirect prompt injection, expose the $500 unauthorized refund and the customer-PII leak as hard evidence, and patch it with a goal-derived intent guard that's injection-agnostic — zero string-matching, and gated in CI so the hole can't reopen.

### How we built it

Using Typescript and HTML

### Challenges we ran into

Nothing

### Accomplishments we're proud of

Everything

### What we learned

A lot

### What's next

Have it become software

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- HTML (language) — claimed on Devpost, not found in the code
- TypeScript (language) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.