1199 matches found
lfi
Lightweight Fault Isolation LFI Welcome to the top-level repository for the Lightweight Fault Isolation LFI project. What is LFI? LFI is a system for sandboxing native code. Like WebAssembly and Native Client, LFI isolates sandboxed code in-process i.e., in the same address space as a host...
wasmforge
WasmForge WasmForge compiles Go and C programs to WebAssembly, then packages them as single native binaries. The resulting executables sandbox guest code inside a WASM runtime a per-build fork of wazero. From inside that sandbox, guests get transparent access to networking, raw sockets, Win32 API...
litebox
LiteBox A security-focused library OS !NOTE This project is currently actively evolving and improving. While we are working toward a stable release, some APIs and interfaces may change as the design continues to mature. You are welcome to explore and experiment, but if you need long-term stabilit...
tenet
Tenet - A Trace Explorer for Reverse Engineers Overview Tenet is an IDA Pro plugin for exploring execution traces. The goal of this plugin is to provide more natural, human controls for navigating execution traces against a given binary. The basis of this work stems from the desire to research ne...
flar
flar FLAR is the Fast Light Agent Restrictor. It runs on rocks called gars. It is a simple, lightweight CLI tool in Go to run coding agent CLIs like Claude Code, Antigravity, Codex, Copilot and Reasonix safely inside isolated Bubblewrap bwrap sandboxes. The purpose is to instantly and without...
stavrobot
Stavrobot Stavrobot is a personal AI assistant built with the principle of "all the access an AI assistant needs, and no more". It has all the nice features of an AI assistant, but focuses on sandboxing, isolation, and minimal permissions. It's lightweight and is deployed with only a docker compo...
NemoClaw
NVIDIA NemoClaw: Reference Stack for Sandboxed AI Agents in OpenShell NVIDIA NemoClaw is an open source reference stack for running supported AI agents more safely inside NVIDIA OpenShell sandboxes. It provides guided onboarding, managed inference, network policy, managed integrations,...
bromure
Bromure Secure, ephemeral computing in disposable Linux VMs on macOS. → Full details, screenshots, and downloads at bromure.io This repo ships two sibling apps, both built on Apple's Virtualization.framework: Bromure — every browser session runs in a throwaway Linux VM. Close the window, the VM i...
agent-governance-toolkit
🌍 English | Español | 日本語 | 简体中文 | 한국어 | 繁體中文 Agent Governance Toolkit Ship agents to production without losing sleep 🚀Quick Start · 📋 Specifications · 📦 PyPI · 📝 Changelog -brightgreen !IMPORTANT Public Preview -- production-quality public preview releases...
zerobox
Zerobox Python SDK Python SDK for zerobox. Sandbox any command with file, network, and credential controls. pip install zerobox Installing the wheel drops the zerobox CLI into your environment's bin/ and exposes a Python SDK. For CLI usage, secrets concepts, the full flag reference, performance...
yolobox
██╗ ██╗ ██████╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗ ██╗ ╚██╗ ██╔╝██╔═══██╗██║ ██╔═══██╗██╔══██╗██╔═══██╗╚██╗██╔╝ ╚████╔╝ ██║ ██║██║ ██║ ██║██████╔╝██║ ██║ ╚███╔╝ ╚██╔╝ ██║ ██║██║ ██║ ██║██╔══██╗██║ ██║ ██╔██╗ ██║ ╚██████╔╝███████╗╚██████╔╝██████╔╝╚██████╔╝██╔╝ ██╗ ╚═╝ ╚═════╝ ╚══════╝ ╚═════╝ ╚═════╝...
zeroboot
Sub-millisecond VM sandboxes for AI agents via copy-on-write forking Try it curl -X POST https://api.zeroboot.dev/v1/exec \ -H 'Content-Type: application/json' \ -H 'Authorization: Bearer zbdemohn2026' \ -d '"code":"import numpy as np; printnp.random.rand3"' Benchmarks Metric| Zeroboot| E2B|...
magika
Magika Magika is a novel AI-powered file type detection tool that relies on the recent advance of deep learning to provide accurate detection. Under the hood, Magika employs a custom, highly optimized model that only weighs about a few MBs, and enables precise file identification within...
libloong
LoongArch64 sandboxing library libloong is a 64-bit high-performance LoongArch emulator library designed for embedding and high-frequency scripting. Built on the architecture of libriscv, it provides the fastest 64-bit interpreter performance available, maintaining a compact 18k LOC codebase with...
nexus-os
Nexus OS The Governed Agentic AI Operating System 66 Crates | 675 Commands | 86 Pages | 5,229 Tests | 10/10 OWASP | Zero Stubs Local-first. Air-gappable. Post-quantum ready. Built in Rust. Architecture | Quick Start | Features | Audit Status | Docs Nexus OS is an AI agent operating system where...
Project-Onyx
Project Onyx Advanced EDR Evasion via AI Telemetry Spoofing & WASM Sandboxing. Project Onyx is a PoC Red Team pipeline designed to demonstrate advanced evasion techniques against modern EDR systems. It shifts away from traditional signature-based obfuscation towards behavioral camouflage and stri...
mcpguard-dynamic
MCPGuard-Dynamic Kernel-level sandboxing for LLM agent tool calls made through the Model Context Protocol MCP. MCPGuard sits as a transparent proxy between an MCP client the agent / runner and an MCP server subprocess, applying three layered defenses to every tool invocation. The lowest layer is...
Winpayloads
Winpayloads - Python2.7 Undetectable Windows Payload Generation with extras Running on Python2.7 As usual, Don't upload payloads to any online virus checkers Virus Total Detection - Updated 25/01/2019 - 16/68 Detections...
Cordon
Cordon ⚠️ PROJECT DEPRECATED Development on this project has been stopped because someone else was working on the same idea and built a better solution. We highly recommend checking out:Fence by Use-Tusk. Note: This repository was originally created forFOSS HACK 2026 , though we unfortunately...
firefox: Information disclosure, privilege escalation in the Security: Process Sandboxing component
A flaw was found in Firefox. The Mozilla Foundation's Security Advisory describes the following issue: Information disclosure, privilege escalation in the Security: Process Sandboxing component...