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

Research code and dataset (WSD) for evaluating audio watermarking impact on anti-spoofing, using wav2vec2 XLS-R and knowledge-preserving learning.
Bypass restricted and censored content on AI chat prompts 😈

3D Passive Face Liveness Detection (Anti-Spoofing) & Deepfake detection. A single image is needed to compute liveness score. 99,67% accuracy on our…

Privacy testing library for deep learning systems, enabling assessment of susceptibility to membership inference, model extraction, and model…

Multi-agent LLM system that autonomously assesses web application security, orchestrating tool-grounded execution and validating exploits end to end.

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

A high-severity prompt injection flaw in Claude AI proves that even the smartest language models can be turned into weapons — all with a few lines of…

Research framework for detecting and removing backdoors in language models, combining feature-based anomaly detection with LoRA-based unlearning…

Proof-of-concept exploit for CVE-2025-23266 (NVIDIAScape) targeting NVIDIA AI container runtime. Demonstrates container escape via GPU driver…

Automated web domain reconnaissance and security assessment tool integrating subdomain enumeration, port scanning, vulnerability scanning, and…

Proof-of-concept demos and research on indirect prompt injection attacks against application-integrated LLMs, covering data exfiltration, remote…

Jailbreaks,Prompt Leaks,Prompt Injection,LLM Attack.Large language model attack prompt collection

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

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

PowerShell-based detection and remediation toolkit for CVE-2025-32711 (EchoLeak), a critical zero-click AI command injection vulnerability in…

Burp Suite extension that uses AI-generated regex strike rules to detect IDOR and access-control flaws, then scans proxy history to find similar…

A service to provide protection against prompt injection, jailbreak attacks, and harmful content when interacting with AI services..

Exploit for Langflow AI Remote Code Execution (Unauthenticated)