
heretic
Fully automatic censorship removal for language models

Fully automatic censorship removal for language models

Open-source framework for red-teaming generative AI systems: automate attack prompts, score model responses, and audit behavior to identify security…

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

Bypass llm guardrails by confusing it with fabricated tool output.

An information security preparedness tool to do adversarial simulation.

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

Clusters and elements to attach to MISP events or attributes (like threat actors)

Windows 10 DLL Injector via Driver utilizing VAD and hiding the loaded driver

C# Reflective loader for unmanaged binaries.

A font-based deception tool for red teaming, security research, and whatever else.

Malware Mutation Using Reinforcement Learning and Generative Adversarial Networks

Generate Linux executables that simulate adversary behaviors and techniques for testing detection and response coverage. Consumes JSON for easy…

A windows token impersonation tool


A tool for generating .NET serialized gadgets that can trigger .NET assembly load/execution when deserialized using BinaryFormatter from JS/VBS/VBA…

A DNS spoofer tool written in Python3.

Playing around with Stratus Red Team (Cloud Attack simulation tool) and SumoLogic

Stop Windows Defender programmatically