
stride-gpt
An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE…

An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE…

Unique tool for fingerprinting Large Language Models based on their tokenizers and behavior.

Artefacts for blog post on finding CVE-2025-37899 with o3

Skills for threat modeling, scanning, triage, patching, plus an autonomous scanning harness you can /customize

Proof-of-concept tool for generating adversarial perturbations to exploit weaknesses in deep learning models, based on DEF CON 25 presentation.

LLM-based vulnerability detection framework combining static code analysis (CFG, DFG, AST) with retrieval-augmented generation for automated…

AI Smart Contract Security Analysis and PoC Generation Framework

LLM based map for research, exploration and discovery.

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…