
CubeSandbox
Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

Instant, Concurrent, Secure & Lightweight Sandbox for AI Agents.

A service to provide protection against prompt injection, jailbreak attacks, and harmful content when interacting with AI services..

Service that builds enrolled open-source repositories in isolated offline VMs and scans them for security vulnerabilities, emailing findings with…

Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

Windows network reconnaissance scanner with ping sweeps, TCP port scanning, and deep AI/ML service detection for finding shadow AI, rogue LLM…

Evidence-focused malware reverse engineering with deep PE/.NET inspection, Ghidra reconstruction, AI cross-checks, YARA, and ELF debugging

Docker Compose lab reproducing CVE-2026-33626 SSRF in LMDeploy's vision-language image loader. Compares vulnerable (0.12.0) and patched (0.12.3)…

eBPF-powered Linux observability with AI incident detection. AGPL-3.0 licensed.

vllm-project vllm version 0.5.2.2 is vulnerable to Denial of Service attacks.