lilbullet.hashnode.devTiny Guards: Defending Agents with small 1-0.6B ModelsPrompt injections and their new rival Prompt injection turns “trusted inputs” (emails, web pages, retrieved docs) into an execution surface. If your agent can browse, read email, or call tools, a buried instruction can hijack actions. The dirty secre...Feb 11·11 min read
lilbullet.hashnode.devBuilding a home local LLM machineMotivation Hello everyone,After engaging with LLMs in different contexts (such as coding, writing, image generation, etc..).I decided I want to test its limitations, barebones, and experiment with it. What better way to do that than by running models...Sep 13, 2025·4 min read
lilbullet.hashnode.devCache Poisoning Leads To DOS On A Customer Service ChatHey everyone, Today, I will talk about a cache poisoning vulnerability that led to DOS on a company customer service chat. First of all, lets discuss on what is a web Cache and how it works (credit to https://portswigger.net/web-security/web-cache-po...Dec 15, 2024·5 min read
