safety-awareness

Transfer Safety Awareness for Cross-Modal Safety Drift Official implementation of Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models EMNLP 2026 Findings. This repository contains the Qwen3-VL safety-awareness direction pipeline. It extracts a refusal-relate...

llm-agent-testbed

🛡️ LLM Agent Security Testbed Empirical Vulnerability & Defense Harness for Tool-Calling LLM Agents A disciplined security testbed testing whether tool-equipped LLM agents can be manipulated into unauthorized data exfiltration via prompt injection, role-claim social engineering, and confused-deput...

FuzzingBrain-Bench

FuzzingBrain Bench A benchmark for LLM-driven vulnerability reproduction on 77 real zero-day bugs across 43 open-source projects C / C++ / Java. Each challenge gives the agent only the fuzz harness the target and the project source at the vulnerable revision — no patch, no fix commit, no target...

qlcoder

QLCoder Agentic Framework for Synthesizing CodeQL Queries Table of Contents Overview Installation Docker Recommended Native Linux Usage Quick Start Development Tooling Examples Paper Environment Contributions Team Citation Affiliated Projects Overview QLCoder is a framework for using LLMs to...

AIDebug

AIDebug Reviewer starting point Evidence-focused reverse-engineering CLI. Andrey Pautov develops the Python analyst interface, offline triage, string intelligence, PE inspection and reporting workflows. Capstone, Ghidra, GDB and optional AI providers are integrations, not original tools authored ...

CopyFail-Experiment

Just an experiment to verify that the LLM can find this vuln and construct a working exploit. Usage gcc -o poc poc.c ./poc...

aegis-latent-core

Aegis Latent Core The evidence gateway for AI systems that must be explainable after the fact. Aegis sits between your application and one or more LLM providers. It admits, bounds, redacts, forwards and records governed calls, then emits portable cryptographic evidence that an independent verifie...

Sentinel-GPT

Sentinel-GPT: Agentic AI for Threat Hunting 🛡️ An automated cybersecurity pipeline that transforms raw Azure logs into actionable intelligence using LLM-based reasoning. 📖 Overview Sentinel-GPT is an AI Agent specialised for threat hunting in cybersecurity. It is integrated with Azure Log Analytic...

ADBloodHound-AI

ADBloodHound-AI AI-Powered Active Directory Attack Path Analysis Analyse de chemins d'attaque Active Directory avec Intelligence Artificielle English | Francais Architecture +---------------------------+ | BloodHound JSON Export | | users, groups, ACLs | +-------------+-------------+ | v...

CVE-2026-0766

CVE-2026-0766: OpenWebUI Remote Code Execution Educational Security Research Repository This repository contains proof-of-concept exploitation code for CVE-2026-0766 , a remote code execution vulnerability in OpenWebUI discovered and published by the Zero Day Initiative ZDI. ⚠️ Disclaimer This...

LeakGauge

LeakGauge This is the code repository for our paper: The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges. ArXiv version and paper link: https://arxiv.org/abs/2608.17829 This repository implements the LeakGauge pipeline for leakage detection: demo dataset preparation,...

scambuster

Automated Scambaiting Honeypot & Threat Intelligence Platform Most security programs block and forget: the mail goes, the attacker's infrastructure and money rails stay unobserved. ScamBuster engages instead, inbound-only and under policy, turning the exchange into IOCs, actor profiles and tagged...

DVDR_LLM

DVDR-LLM: When Are LLMs Better Together for Software Vulnerability Detection and Repair? Official implementation and artifact for the research paper: "DVDR-LLM: When Are LLMs Better Together for Software Vulnerability Detection and Repair?" 🎯 Overview DVDR-LLM is an ensemble framework that...

DCVD

project/ ├── train.py ├── dataloader.py ├── README.md ├── requirements.txt ├── models/ │ ├── controlpathway.py │ ├── semanticpathway.py │ ├── featurefusionmodule.py │ ├── transformerllmmodule.py │ └── multitaskpredictor.py Data and Model Sources Dataset We use the LineVul dataset for vulnerabilit...

isa_recovery

ISA Recovery System A reverse-engineering pipeline that turns a firmware binary and its possibly-wrong disassembly into a working Ghidra processor specification. When you hit a proprietary processor with no documentation and no Ghidra support, this tool recovers the real encoding of each...

ShadowMem

ShadowMem: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory This repository contains the official code release for the paper Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory. ShadowMem is a defensive framework that maintains a dedicated, safety-focused...

CVE-2025-3248

CVE-2025-3248 — Exploit RCE para Langflow Exploit de ejecución remota de código RCE para aplicaciones Langflow vulnerables a CVE-2025-3248. Endpoint afectado: /api/v1/validate/code 🚀 Características del Exploit 🔓 RCE remoto y sin autenticación 🔐 No se requiere autenticación 🐍 Script de una línea ...

delirium-ai-safety-benchmark

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

prompt_injection

Cross-Surface Prompt Injection Benchmark Benchmark for measuring where in a tool-using LLM agent's execution pipeline a prompt injection defense fires — and where it doesn't. Embeds unique canary tokens SECRET-A-F0-98 in injected payloads and tracks them at four pipeline stages: exposed → persist...

SEW

SEW: Style-Encoded Watermarking of LLM-Generated Code Paper Link 📖 📰 News 📢 NEW! The SEW paper is available on arXiv: arXiv:2609.39414. Sep 30, 2026 📢 The official SEW code has been released on GitHub. Sep 30, 2026 🔍 Motivation Feature| Token-level watermarks KGW, SWEET, Unigram, STONE, STA-1|...