mantis - A modular, stack-agnostic toolkit for AI coding ag

项目说明

Mantis: Portable Toolkit for Building Secure Software

> [!CAUTION] USE AT YOUR OWN RISK. BE EXTREMELY CAREFUL. This suite is
> designed to generate and execute autonomously generated code that may be
> unstable or perform unexpected actions. **USE THIS ONLY IN ISOLATED,
> RESTRICTED EN.** Never run this suite on a machine with access to
> production systems, sensitive data, or internal networks.

> [!IMPORTANT] RESPONSIBLE USE AI models are non-deterministic and can
> hallucinate findings or generate incorrect patches. **All findings must be
> manually by a security expert before being reported.** Do not
> mass-file un, AI-generated reports to open-source maintainers. A
> failure to automatically reproduce a does not definitively mean
> it is a false positive, nor does a successful reproducer guarantee the bug is
> exploitable in all contexts. Use Mantis responsibly.

Mantis is a set of skills along with an ADK reference harness for building
secure software in the new AI era of software de.

Getting Started

First, install python3-venv such as with sudo apt install python3-venv, then
run the install script. Mantis comes with automated configuration and launcher
tools (mantis-configure and mantis-launch):

O of Mantis

Mantis is roughly designed to:

Review history of a codebase to look for historical we do not

wish to repeat

Build a semantic index (and/or summaries) of the codebase for efficient code

na

Automatically generate a threat model

Build up a set of hypotheses for indi agents to research (or simply

"scan every file")

Execute on those research plans

Deduplicate existing findings

Triage/critique findings to combat hallucination and statically

production

Reproduce the to degrees, depending on a

en, anywhere from a static guess at what an exploit might look up up
to a unit test or e up a mock server to attempt to exploit

Look across known to attempt to build more impactful chains

Patch discovered , using an ad loop to the

is really fixed

Calibrate all findings based on an established rubric to combat LLM inflation

of se (surfacing the most critical risks to humans instead of spewing
thousands of "criticals")

Reflect on each iteration of the loop to look for things we' in the

now completed round of research

Based on all of the collected learnings, threat model, and knowledge base, use

the /mantis-advise skill to develop code more securely and ensure that
during de you do not repeat prior mistakes or trigger edge cases in
code that were pre protected by some guard that was removed

Additionally, the ADK reference harness shows some of the neat ways in which we
can build agentic workflows. Specifically, reference/workflow.json shows how a
deep review is done, and research graph synthesis
(./run.sh target --objective "...") allows generating custom graph topologies
on the fly. This is a very powerful construct because you can use this to build
any kind of agentic deep di review you might imagine.

Mantis is intended to be a starting point rather than a rigid set of
instructions. You should adapt, tune, and extend this harness to fit your
organization's specific software or hardware stack. We provide an ADK-based
reference harness which works out of the box, but any competent coding agent
should be able to convert this to use your framework of choice.

The Mantis skills can be adapted to
specialized domains (such
as Hardware/RTL, Infrastructure as Code, ML pipelines, or compiled firmware).

We strongly recommend using AI to iterate on these skills and using your
internal documentation, coding standards, and build systems to augment the
threat models you use for scanning. We also strongly recommend adapting risk
calibration to your en and risk tolerance.

Above all, while orchestrated discovery is incredibly powerful and
useful, it is even more important to use this in a suitably isolated en
to prevent impacting production systems. The ADK reference harness provides some
example sandboxes for testing, but if you use the most ad frontier models
you should go beyond this and additionally set up an additional sandboxing layer
that itself contains very strong monitoring to look for escape attempts.

Disclaimers

This is not an officially supported Google product. This project is not eligible
for the
Google Open Source Software Rewards Program.

This project is intended for demonstration purposes only. It is not intended for
use in a production en.

项目信息

开发语言：Python

Star 数：2324

技术要点

该项目属于漏洞知识库方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A modular, stack-agnostic toolkit for AI coding agents to autonomously find, reproduce, and patch vulnerabilities.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。