
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…

Build guide for Red Teaming home lab. GOAD lab setup in Proxmox and pfSense, Operator/C2 and Redirectors.

The exploit server for out-of-band findings. Point a target at a domain you own. Every HTTP request and every email it sends back lands in a…

Research code for poisoning attacks on the PGM-index, demonstrating how to craft adversarial data to degrade learned index performance.

Bypass llm guardrails by confusing it with fabricated tool output.

:cloud: :zap: Granular, Actionable Adversary Emulation for the Cloud

Self-Defeating Audits: reproducible lab showing a low-privilege PostgreSQL role reversibly blinding a trigger-based auditor + poisoning attribution…

A privacy-first app that strips AI watermarks from content you own.

PoC funcional de CVE-2026-17106 (CopyEscape): carrera TOCTOU en docker cp que permite escritura arbitraria en el host Docker. Laboratorio Docker +…

PoC repository for the blog post CopyEscape: Taking Over Docker Hosts with docker cp

Docker Container-to-Host Remote Code Execution POC via vllm-metal trust_remote_code=True

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

Empire is a post-exploitation and adversary emulation framework that is used to aid Red Teams and Penetration Testers.


A simple ptrace-less shared library injector for x64 Linux

HyperDeceit is the ultimate all-in-one library that emulates Hyper-V for Windows, giving you the ability to intercept and manipulate operating system…

Exploit PoCs for CVE-2025-30374, a Taipy class pollution bug, demonstrating RCE, reflected XSS, DoS, and OpenAI credential leakage with Docker-based…

Reproduces CVE-2026-21019 by manipulating node clock to force early Kubernetes CronJob execution; includes vulnerable YAML manifest and Python…