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

A WordPress plugin exposing an MCP server over the REST API, with the security model as the point -- closes the CVE-2026-15015 OAuth-bypass shape by…
Implementation of the paper "Rethinking Latency Denial-of-Service: Attack the LLM Serving Framework, Not the Model"

A listener profile for the Mythic C2 framework that utilizes AI vendors file API's

Defense framework that mitigates malicious fine-tuning of LLMs using selective layer recovery and dynamic routing, with training, harmfulness…

Standard-library Python security triage engine that scans web apps, APIs, LLMs, and mobile packages via passive header inspection, active canary…

Linux privesc enumerator that confirms exploitability and gives you the exact root shell command - no GTFOBins searching. MCP server + AI-agent…

Embeds and detects keyed, style-based watermarks in LLM-generated Python, Java, and C++ code via CST rewriting, preserving functional correctness and…

Agentic jailbreak framework for LLM-based agents using scheme-based task decomposition, multi-turn disguising strategies, and adaptive self-evolution…

A lifecycle benchmark for black-box LLM extraction attacks, defenses, and adaptive attacks.

Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted,…

Code and results for the QAI 2026 paper on FGSM attack transferability from simulation to IBM quantum hardware.

Static analysis CLI that scans codebases for LLM prompt-injection, data-exfiltration, jailbreak, and unsafe agent/tool vulnerabilities. Runs fully…

Reference implementation for "Hard Stop: Kernel-Level Preemption and Containment for Rogue Agentic Execution". Out-of-band Epistemic Andon Cord,…

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Open framework for RL-based prompt injection red teaming, with a shared trainer, curriculum learning, and benchmarks like AgentDojo, InjecAgent, and…

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Hashcat rule analyzer and interpreter - A Rosetta Stone for decoding hashcat rule syntax

Benign, self-contained reproduction of CVE-2026-61732 (Decepticon ChatML role-boundary forgery)