
AISVS
The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

The AI Security Verification Standard (AISVS) focuses on providing developers, architects, and security professionals with a structured checklist to…

LLM-driven agentic group shilling attack framework that manipulates black-box collaborative-filtering recommender rankings using adaptive multi-role…

Detects LLM context-leakage attacks by training lightweight behavior probes on log-probabilities, with vLLM offline/server detection pipelines.

During the exploitation phase of a pen test or ethical hacking engagement, you will ultimately need to try to cause code to run on target system…

Curated reading list and taxonomy of attack and defense research for mobile on-device AI systems, covering adversarial, backdoor, model stealing, and…

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

Proof-of-concept exploit for CVE-2026-73292: CSRF attack on Semaphore UI password change endpoint, serving a malicious page that silently resets an…

Spawns macOS programs through launchd's private XPC interface without execing them, making EDR record launchd as parent. Supports one-shot,…

Windows Defender patch bypass PoC for CVE-2026-50656 (RoguePlanet), demonstrating exploitability on Windows 11 25H2 and Server 2025 despite…

A simple PoC on the Remote Code Execution (RCE) Vulnerability of CraftCMS designated as CVE-2025-32432 written in Go

Proof-of-concept exploit for CVE-2026-22003 demonstrating Redis Lua sandbox escape via debug.sethook to execute arbitrary system commands.

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

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…

reverse engineering Gemini's SynthID detection

The Security Toolkit for LLM Interactions

Adversary simulation and Red teaming platform with AI

This is the tool to dump the LSASS process on modern Windows 11

Benchmark for evaluating AI agent safety against attacks embedded in skill-facing context, with 155 cases across 6 risk domains, measuring task…