
autoguardrails
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

This novel way of using NtQueueApcThreadEx by abusing the ApcRoutine and SystemArgument[0-3] parameters by passing a random pop r32; ret gadget can…

Delving into the Realm of LLM Security: An Exploration of Offensive and Defensive Tools, Unveiling Their Present Capabilities.

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

A tool to find folders excluded from AV real-time scanning using a time oracle

Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks

reverse engineering SynthID for text

A structured knowledge base covering AI security fundamentals, threat modeling, red team offensive techniques, and blue team defenses, including LLM…

Purpleteam scripts simulation & Detection - trigger events for SOC detections

Evolutionary LLM jailbreak and guardrail framework that grows a reusable strategy pool via genetic mutation, Markov selection, and online adversarial…

Windows 7 UAC Bypass Vulnerability in the Windows Script Host

Detect EDR's exceptions by inspecting processes' loaded modules

Library that eases the use of indirect syscalls. Quite interesting AV/EDR bypass as PoC.

Tired of looking at hex all day and popping '\x41's? Rather look at Lugia/Charmander? I have the solution for you.

Payload for DLL sideloading of the OneDriveUpdater.exe, based on the PaloAltoNetwork Unit42's blog post

Open-weight LLMs and training/evaluation code for defending against prompt injection attacks, with benchmarks for agentic tool-calling and…

An autonomous red-teaming engine for LLMs. RedThread manages the full security lifecycle: generating adversarial attacks, executing precision…

Modern PIC implant for Windows (64 & 32 bit)