

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

Tracking Januscape (CVE-2026-53359), the KVM/x86 guest-to-host escape

Tracking ITScape (CVE-2026-46316), the KVM/arm64 guest-to-host escape

EasySec helps small and medium-sized enterprises (SMEs) with cybersecurity knowledge and resources

Portable, hardware-backed WebAuthn credentials using TPM 2.0. Deterministic parent key derived from a master seed enables cross-device credential…

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

Zapscape (CVE-2026-64561) KVM/x86 shadow MMU UAF guest-to-host escape PoC mirror — V4bel/@v4bel, MIT; for authorized security testing

Generates reproducible CORE network topologies from XML scenario files for cybersecurity training and experimentation. Provides Web GUI and CLI for…

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

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

kali-linux-docker

POSIX.1e capability library for Android 10, addressing CVE-2023-2603 with tools for setting and getting process capabilities to manage privilege…

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

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

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

Bypass llm guardrails by confusing it with fabricated tool output.