LLAMATOR-Core/ai-agents-security

Инициатива, посвященная безопасности агентов на базе искусственного интеллекта

40
/ 100
Emerging

This project provides interactive examples of AI agent systems that are vulnerable to attacks like prompt injection and jailbreaking. It helps security researchers and developers understand how these agents can be exploited. You can input attack prompts or automated attack scripts, and observe how the AI agent's intended behavior can be manipulated or bypassed.

No commits in the last 6 months.

Use this if you are a security researcher, AI developer, or penetration tester looking to identify and understand vulnerabilities in AI agent systems through practical, hands-on examples.

Not ideal if you are a general user seeking to build or deploy AI agents without focusing on their security implications.

AI Security Prompt Engineering Penetration Testing Vulnerability Research AI Development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 15 / 25

How are scores calculated?

Stars

53

Forks

8

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jun 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/LLAMATOR-Core/ai-agents-security"

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