
PyRIT
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to…

A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)

A DNS spoofer tool written in Python3.

Exploits the Windows Server 2025 dMSA privilege escalation vulnerability to enumerate writable OUs, escalate to arbitrary domain users, extract…

PurpleSharp is a C# adversary simulation tool that executes adversary techniques with the purpose of generating attack telemetry in monitored Windows…

C# Reflective loader for unmanaged binaries.

A payload delivery system which embeds payloads in an executable's icon file!

PE obfuscator with Evasion in mind

Apply a divide and conquer approach to bypass EDRs

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Modular LLM vulnerability scanner that probes for hallucination, data leakage, prompt injection, jailbreaks, and toxicity using static, dynamic, and…

Hardware Breakpoint (DR0-DR7) based patch-less user-mode hooking & telemetry instrumentation engine (AMSI, WLDP & ETW PoC).

A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in…

A simple PoC on the Remote Code Execution (RCE) Vulnerability of CraftCMS designated as CVE-2025-32432 written in Go

A curated list of useful resources that cover Offensive AI.

CEREBRO-RED v2: Advanced LLM Red Team Research Platform with PAIR Algorithm and LLM-as-a-Judge Evaluation

Benchmarking framework for evaluating computer-use AI agents against multi-step indirect prompt injection, with automatic adversarial goal…

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…