Right now, its's only been a month since launch and currently 123+ businesses have used this
Hey HN!For that last 8 months I've been trying to make agents that can hack web applications to find vulnerabilities in them - An AI Security Tester.The system has 29 agents in total, a custom LLM Orchestration framework which works on the task-subtask architecture (old-school but works amazingly for my use case, and is pretty reliable) with custom agent calling mechanism.No Auo-Gen, Langchain...
I Built an AI Security Tester to test out your web apps for vulnerabilities (sqli, xss, csrf, insecure headers, etc), Business logic flaws, or exposed credentials (You won't believe how many "vibe coders" are exposing their API Keys )Each test initiated is completely unique in how its carried out, adapted to the target website + Gives a security report.On the backend, it runs with the help of...
Wouldn’t it be crazy if, in the future, computers were “hacking” other computers?Imagine an army of AI systems working together - autonomously defending critical infrastructure, detecting and neutralizing threats in real-time. No human intervention. Just machines protecting machines.That’s the future we want to build at Peneterrer.And the first step? Building the AI Penetration TesterThink of...
For the past three months, I've been developing a tool called Peneterrer. It's an LLM-based system that utilizes a Multi-Agent architecture to identify bugs and security threats in websites. The goal is to create an early iteration of a fully Automated Ethical Hacking tool.
I'm eager to hear your thoughts, feedback, or suggestions on how I can enhance this project.
https://github.com/Itachi-Uchiha581/Auto-Trader
Hi HN! I made this as a side project, but astonishingly, it actually turned out to be profitable for me (Paper Trading).In short, the algorithm works in the following way: 1. It discovers trending and profitable stocks provided by the Alpha Vantage API through news sentiment analysis.2. Now, having a list of good stock options, it cherry-picks those stocks that it considers to be from...
Currently, for the backend, tools like Nmap, Dirsearch, ZAP, etc., are employed. When a user asks specific queries like 'Check all open ports in my web app,' 'Check security headers of my app,' or simply 'Find all vulnerabilities in my web app,' it writes commands for the above tools, executes them, and provides the answer. This mix-and-match of tools using simple words allows users to create custom workflows that may run weekly, monthly, or fortnightly.
Hi HN! I am a 14-year-old building Peneterrer. It is a tool for web and solo developers to check their website's security with easy-to-read reports and custom testing workflows.The Main objective of Peneterrer is to make the lives of web developers easy, and it does this by allowing web developers to test their websites by simply using words.Until now I have spent around 3 months creating this...
https://github.com/Itachi-Uchiha581/Auto-Data
Hi HN, I was working on this tool to generate Data for fine-tuning of LLM's as I realised that there was not any single, easy-to-use yet customisable library to do so for my use case.I was wondering about adding LLM data analytics to it as well, would love to hear whether that would be a nice feature to add.