
CUAHarm
Benchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…

Benchmark for evaluating safety risks of computer-using agents, with 104 realistic misuse scenarios across seven malicious categories, supporting…

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

BPF LSM blocker for CVE-2026-31431 (Copy Fail) - zero-reboot remediation for OpenShift 4

Open-source sandboxed runtime for AI agents — gVisor/Docker isolation, credential vault, immutable audit log. Built after CVE-2026-25253.

Rootless container runtime and sandbox that launches kernel-enforced OCI images in milliseconds with no daemon, featuring resource profiles, seccomp…

Secure and fast microVMs for serverless computing.

Sandboxes containers via a userspace application kernel that intercepts system calls, limits host kernel access, and integrates with…

An open-source, next-generation "runc" that empowers rootless containers to run workloads such as Systemd, Docker, Kubernetes, just like VMs.

Benchmarking framework for evaluating computer-use AI agents against multi-step indirect prompt injection, with automatic adversarial goal…

Scripts to build Kali cloud images (fork of https://salsa.debian.org/cloud-team/debian-cloud-images)

Kata Containers is an open source project and community working to build a standard implementation of lightweight Virtual Machines (VMs) that feel…

Lord Of Active Directory - automatic vulnerable active directory on AWS

Exploit KVM/x86 guest-to-host escape CVE-2026-64561 with Zapscape, a proof-of-concept demonstrating hypervisor vulnerability.

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.

Reference analysis of a Linux kernel Open vSwitch memory-corruption vulnerability, covering root cause, impact, detection commands, and mitigation…

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

kali-linux-docker

Assesses a system for the "speculative execution" vulnerabilities described in CVE-2017-5715, CVE-2017-5753, CVE-2017-5754