#1LLM security, prompt injection, model extraction, adversarial AI, and AI red teaming tools.
Kitploit recommended

Detailed security advisory for CVE-2025-492025, documenting a UI misrepresentation vulnerability in Copilot AI that injects unintended hyperlinks…
LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…

Technical Details and Exploit for CVE-2024-11394

Deterministic benchmark and evaluation harness for persistent-memory poisoning in LLM agents, with paired clean/poisoned cases, LangChain/LlamaIndex…

Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into…

Attack framework for breaking fine-tuning based prompt injection defenses (SecAlign, SecAlign++, StruQ) using architecture-aware adversarial attacks…

Research demonstration of indirect prompt injection attacks to control autonomous LLM-based web agents, with tools for trigger optimization and…

Analyzes LLM internal states and 100+ attention/probability features to train classifiers that detect document poisoning attacks in RAG systems.

Machine learning-based exploit for CVE-2023-1177 vulnerability, enabling automated security testing and exploitation of the identified flaw.

A TypeScript package that provides AI-powered agents for Application Security (AppSec) tasks, built on top of the frontier models.

A novel adversarial attack on LLM based on the Exponentiated Gradient Descent technique.

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)…

This study analyzes Python pickle deserialization vulnerabilities, focusing on CVE-2024-3568 in Hugging Face Transformers' TFAutoModel. We reproduce…

SOC, incident response and SecOps for Linux servers in one agent: learns each host, watches it with zero-token sensors, triages with a small model,…

A PoC for CVE-2024-3660. Arbitrary Code Execution in Keras.

vulnerability in CVE 2025-9998 and solution for those vulnerability with help artificial intelligence

Replication package studying how LLM vulnerability auditors defer to static-analysis evidence, with a tree-sitter C/C++ front end, controlled…

Educational Python target range simulating CVE-2026-22807, an AI supply chain RCE via TOCTOU in model loading. Includes vulnerable library, PoC…