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

Proof-of-concept and full writeup for CVE-2026-47644: Edge Copilot prompt injection via attachment tag breakout leading to cross-tab data…

Deterministic benchmark and evaluation harness for persistent-memory poisoning in LLM agents, with paired clean/poisoned cases, LangChain/LlamaIndex…

Real-time safety guard for AI agents. Check before they act.

Code for "Systematic Evaluation of Adversarial Jailbreaking Attacks and Defenses Across Seven Large Language Models"

Proof-of-concept and patch for CVE-2026-57845: pickle deserialization RCE in Hugging Face datasets' pandas builder, with reproduction script and…

Fire ChatML/Mistral/Llama control-token literals at your self-hosted agent stack and prove role-forgery before an attacker does (CVE-2026-61732).

Benchmark and library for evaluating model-extraction attacks and ownership defenses (watermarking, output perturbation, query detection) on graph…

Beyond the Prompt: Jailbreaking Function-Calling LLMs via Simulated Moderation Traces

Measuring and closing the text–vector integrity gap in offline RAG: margin law, vector-database audits and code-level verification.

PyTorch reference implementation of a fast adversarial training method that prevents catastrophic overfitting via coupled objectives and an EMA-based…

Research code for adding controllable safety experts to LLM layers via two-stage upcycling training, with inference-time safety temperature routing…

Fork optimizado de Bytebot: Agente de IA para control de escritorio. Reducido de 7GB a 1.09GB, parcheada CVE-2026-78250, con documentación viva…

Benign, self-contained reproduction of CVE-2026-77521 (MaxKB prompt-injectable command execution)

Research framework for detecting and removing backdoors in language models, combining feature-based anomaly detection with LoRA-based unlearning…

Weight-level LLM forensics: diff model weights, detect fine-tunes, merges and disguised derivatives, and surface tokens a fine-tune promotes or…

Official Build & Verified Release | Open-source AI pentester that proves every finding. Machine oracles re-run each exploit; verified bugs ship a…

Desktop GUI for the REA reverse engineering MCP: code browser with listing, decompiler and function graph, plus 229 analysis tools and an AI agent in…

Express/TypeScript microservice with a Gemini-powered dual-agent consensus loop that synthesizes and validates advisory content for CVE-2026-96230 in…