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

Two-stage prompt-injection and jailbreak detector: regex gates plus a quantised DeBERTa-v3 ONNX classifier, with image, document, and audio support.…
Zero shot vulnerability discovery using LLMs

openrisk is a tool that generates a risk score based on the results of a Nuclei scan.

SecureML - Securing and Watermarking AL models

An offensive/defense security toolset for discovery, recon and ethical assessment of AI Agents

A collection of servers which are deliberately vulnerable to learn Pentesting MCP Servers.

LlamaStack-RCE: Deterministic Supply Chain Exploitation & Hardening Framework [CVE-2024-50050] Focus on AI Security Research…

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

Ethical, network-isolated Docker lab reproducing CVE-2026-26030 — Semantic Kernel in-memory vector store filter eval() RCE (patched in 1.39.4)

A tool that checks if a TorchServe instance is vulnerable to CVE-2023-43654

Technical analysis of the LangChain serialization injection vulnerability CVE-2025-68664.

Gemini 2.5 Pro nf_tables Red Teaming Case Study (CVE-2023-32233) — LLM Safety Alignment & Responsible Disclosure

A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution…

Open-source security audits for Supabase: a read-only MCP server, a CLI agent and a Claude Skill. Finds RLS misconfigurations, exposed keys and risky…

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)…

Pre-auth RCE scanner for Langflow < 1.8.0 — Route Injection + Vertex Injection → Code Execution (CVSS 9.8)

Detailed security advisory for CVE-2025-492025, documenting a UI misrepresentation vulnerability in Copilot AI that injects unintended hyperlinks…

AI-powered penetration testing assistant using local LLM on linux (Parrot OS)