# Vibe guardian

- **Event:** [Gemini Vibe Code Hackathon – SF](https://cerebralvalley.ai/e/vibe-code-gemini-sf)
- **When:** Sat, Nov 8 at 9:00 AM – 10:00 PM (PST)
- **Where:** 365 Toni Stone Xing, San Francisco, CA
- **Team:** [Nikhil Pujari](https://cerebralvalley.ai/u/mpnikhil)
- **GitHub:** https://github.com/mpnikhil/Codeguardian
- **Demo video:** https://www.loom.com/share/2afa093ba085476585c2afadef86c572
- **Gallery:** https://cerebralvalley.ai/e/vibe-code-gemini-sf/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/vibe-code-gemini-sf/hackathon/gallery/15

15 second video intro: https://www.loom.com/share/3727fd02967d445dab7c8eeb709264e4

1. Problem: AI-generated code contains 322% more security vulnerabilities than human-written code (UC Berkeley, Oct 2025), blocking enterprise AI adoption.
2. Solution: Fine-tuned gemini-2.5-flash-lite advisor model that intercepts coding prompts and injects organization policies + security requirements BEFORE code generation.
3. Results: 83% reduction in critical vulnerabilities across 350 test scenarios. 100% elimination of SQL injection and hardcoded secrets.
4. Innovation: Prevention over detection. Based on Berkeley advisor model research (arXiv:2510.02453)—first application to code security.
5. Impact: Real-time (<100ms), works with any LLM, $12 training cost. Enables safe enterprise AI coding adoption.

---

Markdown version of https://cerebralvalley.ai/e/vibe-code-gemini-sf/hackathon/gallery/15. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt