
MMSkillRisk
Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.

Reproduction lab (A/B Docker) for CVE-2026-23989 — OpenCloud / ownCloud Infinite Scale public-link scope-validation bypass in Reva

Secure-by-default demo lab showing how container hardening (distroless images, non-root, read-only filesystem, runtime-injected secrets) can…

Docker images for testing fuzzers on the Rode0day corpora

CVE-2017-8291 CTF with docker and examples

Docker images and k8s YAMLs for Log4j Vulnerability POC (Log4j (CVE-2021-44228 RCE Vulnerability)

Helper scripts to remaster Linux Live CD images for the purpose of creating ready to use security wargames with pre-installed vulnerabilities to…

Proof-of-concept exploit for CVE-2019-14206, demonstrating arbitrary file deletion in the Adaptive Images WordPress plugin. Includes Docker lab,…

Vulnerable docker images for CVE-2021-41773

Proof-of-concept local privilege escalation exploit for CVE-2024-1086 targeting Linux kernels v5.14–v6.6. Achieves root shell with 99.4% success rate…

Challenge based on CVE-2021-22204 where users send a malicious file to a web application to gain RCE

Intentionally-vulnerable nginx 1.30.0 CVE lab images (CVE-2026-40701/42934/42945/42946) for isolated security research. Lab use only.

Proof-of-concept lab and Python/cURL scripts demonstrating CVE-2026-20896, an authentication bypass in official Gitea Docker images via the…

Some docker images to play with CVE-2021-41773 and CVE-2021-42013