msoedov/agentic_security

项目介绍

An open-source vulnerability scanner for Agent Workflows and Large Language Models (LLMs) Protecting AI systems from jailbreaks, fuzzing, and multimodal attacks. Explore the docs » · Report a Bug »

Agentic Security equips you with powerful tools to safeguard LLMs against emerging threats. Here's what you can do:

Probe vulnerabilities across text, images, and audio inputs to ensure your LLM is robust against diverse threats.

Simulate sophisticated, iterative attack sequences to uncover weaknesses in LLM safety mechanisms.

Stress-test any LLM with randomized inputs to identify edge cases and unexpected behaviors.

Seamlessly connect to LLM APIs and push their limits with high-volume,…

摘自 github.com/msoedov/agentic_security