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

AI-powered MCP server for Flipper Zero. Control SubGHz, NFC, RFID, IR, BLE, GPIO, and more over WiFi using Claude or any MCP client.

Autonomous Rust endpoint security agent combining Ring-0 Windows driver and Linux eBPF pre-execution blocking, YARA detection, MITRE ATT&CK mapping,…

Experimental Linux strace LLM agent

This opensource project dedicated to implementing Enterprise level AI-SPM. By doing so organizations can proactively protect their AI systems from…

Open-source prompt injection attack console. Test AI security by firing categorized attacks at any endpoint.

Next-generation JavaScript identifier recovery with LLMs.

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

Autonomous multi-agent AI penetration-testing engine: a governed tool sandbox, an immutable evidence-and-validation gate, and a reproducible…


Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks

Red portatil de reconocimiento inteligente con IA offline

Scans code diffs with context to build an impact graph and uses LLMs to find vulnerabilities, supporting multi-repo scans and CI gating with SARIF…

An open, local-first security testing platform for pentesters, AI agents, CI/CD pipelines, and teams.

LLM-first deception framework: "The honeypot that talks back!™"

DonkAI is a hands-on lab for the OWASP Top 10 for LLM Applications (2025) - no real LLM required.

A doggo that helps look for security issues in your repositories.

Research implementation for mitigating adaptive prompt injections via on-policy distillation, with training recipes and evaluators for SEP, PISmith,…

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