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

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

CVE-2026-4372: Threat Model, Root-Cause Analysis, Replication & Detection

DugganUSA threat-intelligence contributions to the IETF Hackathon: real-world agentic-attack benchmark vectors, CVE-2026-33697 attestation analysis,…

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

Two-layer LLM firewall that blocks prompt-injection inputs via regex rules plus a Gemini classifier, and catches secret or system-prompt leaks in bot…

Research code for HARDE, an agent harness that probes and adaptively optimizes components for runtime risk detection and execution control across…

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

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

Research code for measuring jailbreak attack success rates (ASR and stepwise ASR) against LLMs, with implementations of attacks such as GCG and…

Security & Compliance bodyguard for OpenClaw agents

Code, derived data and results for: Evaluating Baseline Detectors of Hijacked LLM Agents Under Rare Attacks and Distribution Shift

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

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…

Replication package studying how LLM vulnerability auditors defer to static-analysis evidence, with a tree-sitter C/C++ front end, controlled…

An audit-oriented risk model for how agent-generated inferences can change epistemic status, gain operational authority, and influence later…

Research code for Rubric-Induced Preference Drift (RIPD): evolutionary rubric search, benchmark-preserving selection, and DPO policy misalignment…

Research codebase for privacy evaluation of quantized neural networks: trains target/shadow models under PTQ/QAT and runs membership-inference…

CyberRAG — RAG 100% local (Ollama) sobre apuntes y libros de ciberseguridad: recuperación híbrida, respuestas con citas, asistente de pentest por…