galah

TL;DR: Galah /ɡəˈlɑː/ - pronunciato ‘guh-laa’ è un honeypot web basato su LLM progettato per emulare varie applicazioni e rispondere dinamicamente a richieste HTTP arbitrarie. Galah supporta i principali provider LLM, tra cui OpenAI, GoogleAI, la Vertex AI di GCP, Anthropic, Cohere e Ollama. A...

stride-gpt

STRIDE GPT is an AI-powered threat modelling tool that leverages Large Language Models LLMs to generate threat models and attack trees for a given application based on the STRIDE methodology. Users provide application details, such as the application type, authentication methods, and whether the...

beelzebub

Beelzebub Framework runtime di deception Beelzebub è un runtime di deception open-source che distribuisce servizi esca adattivi basati su LLM sui protocolli SSH, HTTP, TCP, TELNET e MCP. Va oltre i semplici honeypot passivi ingaggiando attivamente gli attaccanti in interazioni realistiche,...

Galah - An LLM-powered Web Honeypot Using The OpenAI API

TL;DR: Galah /ɡəˈlɑː/ - pronounced 'guh-laa' is an LLM Large Language Model powered web honeypot, currently compatible with the OpenAI API, that is able to mimic various applications and dynamically respond to arbitrary HTTP requests. Description Named after the clever Australian parrot known for...