
yoloai
Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

A QEMU/KVM-based USB fuzzing framework that finds device-driver bugs via reproducible VM execution, multiprocessing, and XML testcase generation.

Linux kernel exploitation toolkit providing an exploit-building library, ROP chain and stack pivot generators, kernel image runners, and a target…

PoC exploit for CVE-2026-64561, a KVM/x86 shadow MMU use-after-free enabling guest-to-host escape with kernel root code execution on the host.

Hypervisor isolated shellcode execution environment. Maps host process memory into a guest vCPU, intercepts DLL execute faults, and proxies API calls…

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Docker-based sandbox for coding agents with isolated environments, preinstalled agent tooling, service control, and workspace bootstrap for secure…

Zero-click pre-auth WordPress CVE-2026-93485 exploit chain: stored XSS in wpautop() escalates to admin-session plugin upload and a self-deleting…

WASM sandbox with capability enforcement for AI agent code. Agents can only call explicitly provided tools with defined constraints. Sandboxed…

JIT-based userspace Linux kernel that runs containers natively on Apple Silicon macOS without a VM. Drop-in Docker Engine API replacement with…

An example sandbox using AppContainer (Windows 8+)

Library-Level eBPF Sandbox for Python (Linux & macOS): syscall-level control per module.

Rust AMD SVM hypervisor framework with customizable vmexit handlers (MSR, CPUID, RDTSC) and NPT hooking for kernel-level monitoring and research.

Declarative KVM/QEMU VM orchestration tool using YAML compose files. Manages multi-VM stacks with cloud-init, SSH, PCI passthrough, and image…

Kali Linux Docker

Lord Of Active Directory - automatic vulnerable active directory on AWS

Zero-trust agentic AI platform. Supports SaaS and OnPrem (airgapped) deployments.

Kernel-level eBPF sandbox for securing LLM agent tool calls made through the Model Context Protocol (MCP)