Holistic Application Security — Offensive & Defensive Open Source Tooling

A complete open-source ecosystem for application security. From AI-powered pentesting to LLM guardrails and structured assessment methodologies.

Scroll

Full-spectrum application
security, open source.

$ nmap -sV scanning...

Offensive Security

AI-driven penetration testing, automated vulnerability scanning, and exploit validation. Let intelligent agents find what manual testing misses.

Defensive Security

LLM guardrails, prompt injection protection, and runtime monitoring. Intercept threats before they reach your models and applications.

?

Methodology

Structured assessment frameworks and community-driven knowledge. Repeatable, thorough security reviews built on proven standards.

Built to break, built to protect.

Agent-Smith Offensive

AI-Driven Penetration Testing Agent

Claude orchestrates security tools autonomously—deciding what to run, in what order, and when to stop. Containerized tooling with a real-time dashboard and 50+ integrated security utilities.

Python FastAPI Docker MCP Kali
View Repository
Seraph Defensive

LLM Guardrail Proxy

Intercepts and scans all LLM communications for prompt injection, toxicity, and leaked secrets. Works with any provider—OpenAI, Anthropic, Azure, Ollama. Three integration modes: Direct Scan, Gateway Hook, Transparent Proxy.

Python FastAPI llm-guard
View Repository
Oracle Methodology

Whitebox Security Assessment Methodology

A structured, step-by-step guide for comprehensive application security assessments. Built for security champions and AppSec engineers embedding security into the development cycle.

Jekyll Markdown
View Repository
Skills Knowledge

Security Skills & Knowledge Base

Curated collection of pentesting skills covering AI red teaming, container security, OSINT, threat modeling, network assessment, and more. Community-driven and open for contribution.

AI Red Team OSINT K8s Threat Model
View Repository

A continuous security lifecycle.

Every tool feeds the next. Methodology informs testing, testing reveals what to defend, defense generates knowledge, and knowledge refines the methodology.

Oracle Define methodology
Skills Learn & share
Agent-Smith Attack & discover
Seraph Defend & protect

Continuous cycle — knowledge feeds back into methodology

Build with us.

NullPointer is fully open source and community-driven. Whether you're a pentester, security engineer, or developer—there's a place for you. Contribute code, share knowledge, or just hang out.