
ZORG-Jailbreak-Prompt-Text
Bypass restricted and censored content on AI chat prompts 😈

Bypass restricted and censored content on AI chat prompts 😈

A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

NimicStack is the pure Nim implementation of Call Stack Spoofing technique to mimic legitimate programs

Port of Cobalt Strike's Process Inject Kit

Leak NTLM via Website tab in teams via MS Office

Research implementation of a poisoning attack against retrieval-augmented language models using camouflaged documents to evade filtering defenses and…

HyperDeceit is the ultimate all-in-one library that emulates Hyper-V for Windows, giving you the ability to intercept and manipulate operating system…

Command-line utility for Windows that enables SeTakeOwnershipPrivilege and modifies file ownership to the current user, granting access to otherwise…

A toolset to make a system look as if it was the victim of an APT attack

Research demonstration of indirect prompt injection attacks to control autonomous LLM-based web agents, with tools for trigger optimization and…

Crystal Palace library for proxying Nt API calls via the Threadpool. Updated for call gadgets.

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

Abuses Windows Filtering Platform to launch a console as NT AUTHORITY\SYSTEM or impersonate another logged-on user for privilege escalation during…

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

PoC simulation of a critical CCSDS telecommand replay vulnerability in satellite command systems, demonstrating missing sequence-number validation…

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

A windows token impersonation tool

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