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

Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
A minimal LLM-powered zero-day vulnerability scanner by AISLE.

Playbook-based adversary simulation framework that compiles JSON-defined attack paths into position-independent shellcode payloads for validating…

The Anti-Virus for AI Artifacts & RAG Firewall. A static analysis tool scanning Models and Notebooks for RCE, Datasets and RAG docs for Data…

Security scanner for MCP servers. Grades auth, permissions, injection risks, and tool safety. The Lighthouse of agent security.

The OWASP Subtractive Security Top 10 Project is an initiative to identify, document, and promote the highest-impact opportunities for reducing cyber…

This repository provides the official implementation of POISONCRAFT: Practical Poisoning of Retrieval-Augmented Generation for Large Language Models.

Security & Compliance bodyguard for OpenClaw agents

Recon-Scan: open‑source passive reconnaissance with AI‑powered security analysis. Zero‑touch, developer‑first, and privacy‑focused.

Silent dependency injection through AI documentation pipelines. 240 isolated Docker runs proving Context Hub's zero-sanitization MCP server lets…

Expose and detail an unauthenticated stored XSS vulnerability in the Google Cloud Vertex AI Python SDK affecting versions 1.98.0 to 1.130.9.

Implementation of optimal coupling-based distortion-free text watermarking to embed detectable signals in LLM-generated text while preserving quality.

CVE-2026-40487

CVE-2025-31337 Security Advisory - Critical Buffer Overflow in AI Chatbot Framework

Security research lab — Unauthenticated RCE via insecure deserialization in ComfyUI v0.23.0 (CVSS 9.8). Isolated Docker environment, technical…

Proof-of-concept and research repository for CVE-2024-37054, an unsafe deserialization flaw in MLflow PyFunc model loading that can lead to remote…

Research code and experiments for defending tool-integrated LLM agents against adversarial attacks, extending Agent Security Bench with new defense…

Autonomous AI agent with its own crypto identity — hunts CVEs, builds exploit labs, validates vulnerabilities (first public PoC of CVE-2026-86283),…