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

Pre-install security for AI agents, npm packages, and MCP servers. Zero-dep local static analysis; normal scans never execute package code.


A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion (ACE) and related liminal attack vectors. **Delirium** is not…

Autonomous AI pentesting engine, continuous offensive security across web, cloud, AD & Kubernetes. Agentic reasoning + real exploit execution deliver…

AI Smart Contract Security Analysis and PoC Generation Framework

AIRecon is an autonomous cybersecurity agent that combines a self-hosted Large Language Model (Ollama) with a Kali Linux Docker sandbox and a Textual…

Provably secure linguistic steganography embedding secret messages into LLM-generated text via rotation range-coding. Includes embed, extract, and…

CVE-2026-40487

AI-powered offensive security testing using autonomous agents, directly in your terminal.

ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities designed to evaluate AI agents' ability to develop exploits.

Code for ACL 2026 (main) paper "DeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation"

Code repository for CS5446 project exploring defenses against jailbreak attacks on large-language models it includes datasets, notebooks,…

Detailed technical analysis of CVE-2024-5452, a remote code execution vulnerability in PyTorch Lightning via DeepDiff delta property pollution, with…

Causal context attribution and rule-based monitor LLM defense against indirect prompt injection in LLM agents, achieving state-of-art performance on…

The code in "DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization"

The code of VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Working implementation: cryptographically verified short-lived identities for AI decision authentication — CVE-2025-59536 (Patent Pending US…

VulnAgent-X: A Layered Agentic Framework for Repository-Level Vulnerability Detection