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

Portable security rules for the action boundary of AI agents
Free security-baseline rule for Claude Code, Codex, and Cursor: treats MCP tool descriptions as untrusted input (OWASP MCP Top 10 MCP03,…

Technical webinars on reverse engineering, malware analysis, and software protection.

Proof-of-concept that poisons MLflow registered models via the REST API, embedding a malicious pickle to trigger RCE when the model is loaded.

Experiments for control-token chain-of-thought suppression and parser-leniency attacks on tool-using LLM agents

Measuring Open Privilege in Agent Defenses

Read-only CLI that inventories AI agents, MCP servers, plugins, and extensions on a machine, reporting their capabilities and exposure with…

Lightweight, secure Linux sandboxes for untrusted processes. Runs in the browser and on the server.

Security scanner auditing Claude Code environments for CVE-2026-21852 pre-trust execution, hook hijacking, and eBPF lockdown.

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

Trained to Escalate: Forensic Analysis and Local Replication of RLHF-Induced Privilege Escalation in AI Agents (CVE-2026-65616)

Local AI Capture-the-Flag platform with guided lessons on prompt injection, tool-call abuse, and OSINT against six simulated chatbot personas.

An open-source, self-hosted AI-powered SIEM, EDR and SOAR platform for modern security operations.

Gemini - Production LLM Runtime Alignment Context Injection

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

Sandbox and MCP proxy that blocks AI coding agents from reading SSH keys, AWS credentials, and .env files, with deny-by-default policy and…

AI-powered cybersecurity chatbot designed to provide helpful and accurate answers to your cybersecurity-related queries and also do code analysis and…

Human-in-the-loop UI that converts natural-language or C/C++ protocol descriptions into a reviewable Protocol IR, then generates Sapic+/Tamarin…