
skulto
Offline and security-first tool for syncing and managing agent skills

Offline and security-first tool for syncing and managing agent skills

Capability-based WASM runtime for executing untrusted AI-generated code with enforced CPU, memory, time, I/O, and filesystem limits. Provides…

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.

Rust exploit PoC for Linux kernel LPE CVE-2026-31431 (AF_ALG page-cache write) plus eBPF runtime defense blocking AF_ALG socket creation via LSM or…

eBPF LSM program that blocks AF_ALG socket creation to mitigate CVE-2026-31431, with userspace daemon logging denied attempts via ring buffer.

Proof-of-concept exploit for CVE-2026-2441, demonstrating the vulnerability and providing a working exploit for security testing and validation.

Proof-of-concept demonstrating a Node.js permission model bypass (CVE-2026-21636) that allows network access via undici/fetch to local services,…

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.

Manages the core lifecycle of Qubes OS domains via a Python admin API, handling secure compartmentalization with Xen and exposing an event system for…

Code for paper "ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents"

Runtime security gateway for AI agents: cryptographically attests tool calls, enforces policies, sandboxes execution, and logs tamper-evident audit…

Kali Linux VM images build script

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)

Kali Linux Docker

Go Trusted Execution Environment (TEE)