
hpim-training-lab
Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

Forensic Analysis and Local Replication of the OpenAI-Artifactory Privilege Escalation Incident (CVE-2026-65616)

Sandboxed runtime for autonomous AI agents with declarative YAML policies enforcing filesystem, network, and process constraints, plus endpoint-bound…

Governed execution cells for AI agents.

The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation…

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

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

OS command injection in KubeAI via an Ollama model URL — CVE-2026-34940 / CVSS 8.7

Proof-of-concept exploit for CVE-2023-5043, demonstrating arbitrary command execution via Ingress NGINX annotation injection in Kubernetes, with a…

Docker-based vulnerable lab for CVE-2026-3288 NGINX Ingress configuration injection, with exploit scripts, detection monitoring, and remediation…

Proof-of-concept for CVE-2026-29955, a command injection vulnerability in KubePlus kubeconfiggenerator allowing remote code execution and…

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

Kubernetes driver extension of the Chaos Toolkit probes and actions API

Real-time cloud-native runtime security agent for Linux that monitors syscalls and container/Kubernetes metadata to detect anomalous behavior and…

A Chaos Engineering Platform for Kubernetes.

Chaos testing, network emulation, and stress testing tool for containers

An easy to use and powerful chaos engineering experiment toolkit.(阿里巴巴开源的一款简单易用、功能强大的混沌实验注入工具)

Structured security knowledge base with production-inspired cases: vulnerability analysis, exploit explanation, remediation, and DevSecOps for…