agentic_security - Agentic LLM Vulnerability Scanner / AI red teaming

项目说明

<p align="center">
<h1 align="center">Agentic Security</h1>
<p align="center">
An open-source scanner for Agent Workflows and Large Language Models (LLMs)<br />
Protecting AI systems from jailbreaks, fuzzing, and multimodal attacks.<br />
<a href=" the docs »</a> ·
<a href=" a Bug »</a>
</p>
</p>

Features

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

Multimodal Attacks 🖼️🎙️

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

Multi-Step Jailbreaks 🌀

Simulate sophisticated, iterati sequences to unco in LLM safety mechanisms.

Comprehensi 🧪

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

API Integration & Stress Testing 🌐

Seamlessly connect to LLM APIs and push their limits with high-, real-world attack scenarios.

RL-Based Attacks 📡

Le reinforcement learning to craft adapti probes that evolve with your model’s defenses.

> Why It Matters: These features help de, researchers, and security teams proactively identify and mitigate risks in AI systems, ensuring safer and more reliable deployments.

📦 Installation

To get started with Agentic Security, simply install the package using pip:

⛓️ Quick Start

UI 🧙

<img width="100%" alt="booking-screen" src="

LLM kwargs

Agentic Security uses plain text HTTP spec like:

Where <<PROMPT>> will be replaced with the actual attack during the scan, insert the Bearer XXXXX header value with your app credentials.

Adding LLM integration templates

TBD

Adding own dataset

To add your own dataset you can place one or multiples cs with prompt column, this data will be loaded on agentic_security startup

Run as CI check

Init config

default config sample

List module

Extending dataset collections

1. Add new metadata to agentic_security.probe_data.REGISTRY

and implement loader into

Dynamic datasets with mutations

One of the current examples uses sampling for the existing preloaded prompt data and applying mutations yielding a new dataset

Probe endpoint

In the example of custom integration, we use /v1/self-probe for the sake of integration testing.

This endpoint randomly mimics the refusal of a fake LLM.

Image Modality

To probe the image modality, you can use the following HTTP request:

Replace XXXXX with your actual API key and <<BASE64_IMAGE>> is the image .

Audio Modality

To probe the audio modality, you can use the following HTTP request:

Replace $GROQ_API_KEY with your actual API key and ensure that the file parameter points to the correct audio file path.

CI/CD integration

This sample GitHub Action is designed to perform automated security scans

Sample GitHub Action Workflow

This setup ensures a continuous integration approach towards maintaining security in your projects.

Module Class

The Module class is designed to manage prompt processing and interaction with external AI models and tools. It supports fetching, processing, and posting prompts asynchronously for model . Check out module.md for details.

Documentation

For more detailed information on how to use Agentic Security, including ad features and customization options, please refer to the official documentation.

Roadmap and Future Goals

We’re just getting started! Here’s what’s on the horizon:

RL-Powered Attacks: An attacker LLM trained with reinforcement learning to dynamically evol and outsmart defenses.

Massi Expansion: Scaling to 100,000+ prompts across text, image, and audio modalities—curated for real-world threats.

Daily Attack Updates: Fresh attack delivered daily, keeping your scans ahead of the curve.

Community Modules: A plug-and-play ecosystem where you can share and deploy custom probes, datasets, and integrations.

| Tool | Source | Integrated |
|-------------------------|-------------------------------------------------------------------------------|------------|
| Garak | leondz/garak | ✅ |
| InspectAI | UKGo/inspect_ai | ✅ |
| llm-adapti | tml-epfl/llm-adapti | ✅ |
| Custom Huggingface Datasets | markush1/LLM-Jailbreak-Classifier | ✅ |
| Local CS | - | ✅ |

Note: All dates are tentative and subject to change based on project progress and priorities.

👋 Contributing

Contributions to Agentic Security are welcome! If you'd like to contribute, please follow these steps:

Fork the repository on GitHub

Create a new branch for your changes

Commit your changes to the new branch

Push your changes to the forked repository

Open a pull request to the main Agentic Security repository

Before contributing, please read the contributing guidelines.

License

Agentic Security is released under the Apache License v2.

🚫 No Cryptocurrency Affiliation

Agentic Security is focused solely on AI security and has no affiliation with cryptocurrency projects, blockchain technologies, or related initiatives. Our mission is to advance the safety and reliability of AI systems—no tokens, no coins, just code.

Contact us

项目信息

开发语言：Python

Star 数：2017

技术要点

该项目属于安全软件方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。

从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。

使用与学习建议

1. 下载源码压缩包，解压到本地环境。

2. 根据项目类型准备对应的运行环境与依赖。

3. 按照 README 中的步骤完成配置与部署。

4. 在隔离的测试环境中运行验证，避免影响生产系统。

免责声明

本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。