Open Threat Research (original) (raw)

Agents Evolving the Threat Hunter Playbook 🏹: Planning Hunts with Agent Skills 🤖 This post shows how the Threat Hunter Playbook can be extended with Agent Skills to structure hunt planning for AI agents, describing known workflows and using progressive disclosure so agents can access knowledge at the right time.

LLM Featured Floki 👁️‍🗨️: Building an AI Agentic Workflow Engine with Dapr⚡️ After building an agent in Python from scratch, it was time to take the next step and build a framework for multi-agent collaboration while exploring the concepts behind agentic workflows. Traditional workflows often focus on well-defined, sequential steps, but agentic workflows introduce a level of adaptability, enabling agents

Agents Featured Rise of the Planet of the Agents 🤖: Creating an LLM-Based AI Agent from Scratch! Ever since I began learning about Generative Artificial Intelligence (GenAI), I've been eager to explore beyond just building AI chatbots for simple question-answering over documents. This curiosity led me to experiment with various LLMs, and through this process, I learned about their potential not only for recalling

Exploring Defensive Challenges with Artificial Intelligence: From Traditional to Generative Recently, generative artificial intelligence (GenAI) has emerged as a game-changer in cybersecurity, significantly enhancing traditional security operations. Its applications range from helping analysts in understanding complex topics during incidents to deciphering intricate scripts, and summarizing findings effectively. With the appropriate fine-tuning, GenAI models can even suggest investigative steps.

Generative AI Demystifying Generative AI 🤖 A Security Researcher's Notes As a security researcher, stepping into the world of Generative Artificial Intelligence (GenAI) was like entering unfamiliar territory. While I was excited by the potential it held for revolutionizing security, I soon realized there were many unfamiliar concepts and terms that were new to me. In this blog post, I