
Securekit
Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent…

Collection of IoCs available and related to attacks on ESXi infrastructures that occurred as of Friday February 3, 2023.


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

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

Proof-of-concept CVE exploit and lab scripts for sandbox/VM isolation, targeting authorized environments such as Docker and virtual machines for…

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

Let your AI go full send. Your home directory stays home.

Main UserLAnd Repository

Easily create full virtual machines that are sandboxed for development or computer use models.

Domain-specific language for writing fast functional device models for virtual platforms. Compiles DML to C with API calls tailored for the Intel…

Script to install prerequisites for deploying GOAD on Ubuntu Linux 22.04

Exploit PoC for CVE-2026-64561: KVM/x86 shadow MMU use-after-free allowing a guest to escape to host root. Includes technical write-up, affected…

CVE-2020-0890 | Windows Hyper-V Denial of Service Vulnerability proof-of-concept code

wasm2c sandbox escape. An untrusted WebAssembly module breaks out of the generated C sandbox and executes an arbitrary shell command on the host.