@DanKornas: Security testing setup gets complicated fast. This repo maps the moving parts. HackerAI is a public GitHub codebase for…
Summary
HackerAI is a public GitHub codebase for an AI-powered penetration testing assistant, offering chat-driven workflows, agent-mode runtime with isolated execution, and guided local setup using Next.js, Convex, and Trigger.dev components.
View Cached Full Text
Cached at: 09/09/26, 07:49 AM
Security testing setup gets complicated fast. This repo maps the moving parts.
HackerAI is a public GitHub codebase for an AI-powered penetration testing assistant.
It helps you stand up a chat-driven agent workflow for security testing by documenting the services and local commands needed to run its Next.js, Convex, and http://Trigger.dev components.
Key features:
• Chat-led workflow – the repo describes finding and fixing vulnerabilities by chatting with AI
• Agent-mode runtime – the README runs the agent loop on a http://Trigger.dev task
• Isolated execution – Agent mode uses E2B for isolated cloud execution
• Guided local start – pnpm run setup and pnpm run dev install and start the local stack
• Required services listed – the README identifies OpenRouter, OpenAI, Convex, WorkOS, and http://Trigger.dev
Public GitHub repo. Its Apache 2.0 license includes additional commercial-use restrictions.
Link in the reply 👇
Similar Articles
@0x0SojalSec: Awesome AI Security : Everyone’s racing to deploy AI agents, Almost few peoples is securing them properly. this repo co…
A curated GitHub repository aggregating frameworks, tools, attack matrices, red team guides, policy templates, datasets, and research for securing AI systems, covering topics like prompt injection, jailbreaking, and OWASP/NIST standards.
@josesilesdata: GOODBYE TO CYBERSECURITY! A repository just came out with hundreds of AI security tools in an open-source repository. T…
An open-source repository containing hundreds of AI security tools has been released, featuring techniques for jailbreaking LLMs, prompt injection testing, red team agents, model extraction, and automated pentesting.
Someone built an agent that tries any github repo in a sandbox and records it.
A weekend project that uses an AI agent to test any GitHub repository in a sandbox environment and records the session as a video to help users evaluate code quality.
How are you testing your AI agents for security before they hit users? We got tired of not having a good answer and built this.
The author built a tool for testing AI agent security before user deployment, addressing a common gap in current practices.
@XAMTO_AI: Open the repository and at first glance, you'd think it was released by Anthropic. The author is mukul975, community di…
An open-source cybersecurity skills library for AI agents with over 800 skills across 34 security domains, designed for authorized penetration testing and security research.