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

Exploits for CVE-2024-14027 creating using AI/Claude as a test.

Small language model that names and describes functions in stripped x86-64 binaries, with an open dataset, baselines, and LoRA fine-tuning…

Offline SAST/DAST triage engine that parses source code and replays HAR traffic to detect business-logic flaws, BOLA, race conditions, and privilege…

Extensión de Burp Suite que incorpora detección pasiva de vulnerabilidades mediante inteligencia artificial.

Tactical Identity Operator for Linux & Hybrid Active Directory

Service that builds enrolled open-source repositories in isolated offline VMs and scans them for security vulnerabilities, emailing findings with…

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its…

Red-teaming benchmark and black-box attack framework for evaluating visual misinformation risks in commercial image generators, with 10k false-claim…

Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models (NeurIPS'26)

Adversarial image attacks on vision-language web agents, from visual grounding to browser execution

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

Zero-retraining sanitization that reorders permutation-equivalent neural network units to destroy malware embedded via weight-steganography attacks…

Research implementation of an LLM jailbreak agent that bypasses commercial model guardrails using harmless prompt weaving and adaptive tree search.

Curated collection of research papers on retrieval-augmented generation security, organized by the SLOT taxonomy covering knowledge poisoning,…

MCP-enabled multi-agent framework for declarative YAML-driven agentic workflows, used for AI-assisted code auditing, vulnerability triage, and…

Example AI-agent taskflows and MCP servers for auditing source code, triaging issues, and detecting vulnerabilities across web, Android, and iOS…

Research code for training adapters that make LLM agent backdoors survive benign fine-tuning, with trigger-rate scoring, SWE-bench evaluation, and…