deadbits/vigil-llm

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

44
/ 100
Emerging

This project helps security and operations teams protect their AI applications by detecting harmful or malicious inputs to Large Language Models (LLMs). It takes user prompts and LLM responses as input and identifies potential prompt injections, jailbreaks, or other security threats, providing an assessment of the risk. Anyone responsible for the security and integrity of applications built on LLMs, especially those in cybersecurity or AI operations roles, would use this.

464 stars. No commits in the last 6 months.

Use this if you are developing or managing an application that uses Large Language Models and need to protect it from common attack vectors like prompt injections and jailbreaks.

Not ideal if you need an enterprise-grade, fully supported AI firewall solution, as this project is currently in an experimental alpha state.

AI security prompt engineering LLM operations cybersecurity application security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

464

Forks

53

Language

Python

License

Apache-2.0

Last pushed

Jan 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/deadbits/vigil-llm"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.