
Aura-State
Python framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…

Python framework for building LLM workflows as state machines with formal verification via Z3 theorem proving, CTL model checking, and conformal…

AI Smart Contract Security Analysis and PoC Generation Framework

Finding vulnerabilities through dumb brute force

Open-source security gateway & static scanner for AI agents. Enforce role-based access control (RBAC), human-in-the-loop approvals, segregation of…

A small tool I made to dump the export table of PE files. The primary use case was intended for use within DLL proxying.

Fix-Like Artifacts With Embedded Defects

SecureAI-Scan is a CLI tool that scans TypeScript and JavaScript codebases for security issues specific to AI-powered apps — prompt injection, MCP…

Pre-execution intent verification for AI agents. Audits what your AI is about to do, not what it says. Zero dependencies, deterministic, hash-sealed.

Educational demo of three Claude Code vulnerabilities (hooks bypass, MCP injection, API key exfiltration) with attacker server, MITM proxy, and…

100% Free & Open Source • Privacy-First Security Scanning and AI Code Review CLI

Demo showing Claude Opus does not find CVE-2023-0266

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

A doggo that helps look for security issues in your repositories.

Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.

Official code for the ISSTA 2026 paper: Is "Knowing It’s Malicious" Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing

Evidence-focused malware reverse engineering with deep PE/.NET inspection, Ghidra reconstruction, AI cross-checks, YARA, and ELF debugging

A benchmark for evaluating AI agents on fixing real-world security vulnerabilities.

Proxy server that wraps MCP servers with behavioral profiling, security scanning, risk gating, and safe execution. Detects prompt injection,…