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

DonkAI is a hands-on lab for the OWASP Top 10 for LLM Applications (2025) - no real LLM required.
Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

A curated list of useful resources that cover Offensive AI.

A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow, and JAX

A static + runtime security scanner for MCP (Model Context Protocol) servers

Self-hostable AI SOC that fuses security alerts, auto-triages via agentic AI, runs MITRE ATT&CK investigations, and logs every agent decision in a…

The independent security agent for AI-written software. Finds issues, investigates whether they are real, and shows you the evidence. Deterministic…

Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run,…

Research code for detecting and detoxifying backdoors in text-to-image diffusion models, with pipelines for Stable Diffusion v1.4, v1.5, XL, and 3…

Standardized adversarial robustness benchmark with a public leaderboard and downloadable model zoo for evaluating ML models against Lp attacks and…

Research-only AI watermark robustness toolkit: local reverse proxy strips C2PA/EXIF/XMP, Unicode, image/audio stego, OOXML/PDF metadata, and scans…

A cybersecurity research game measuring how humans detect AI-generated phishing emails. Built as a retro terminal experience.

Secret-Use Delegation Protocol — protocol-level secret use for agentic systems

Visibility into AI agent activity on endpoints, with on-device detection, optional pre-action blocking, and forensic reconstruction.

Black-box input-stage purification defense that neutralizes backdoor attacks on object detectors via corruption, diffusion reconstruction, and DBSCAN…

Iterative agent harness that uses LLMs and Certora Prover to generate and refine smart-contract CVL specs, feeding verifier output back until success…

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…

☸️ The Testing Platform for the agentic SDLC