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...

morty

Morty Web content sanitizer proxy as a service Morty rewrites web pages to exclude malicious HTML tags and attributes. It also replaces external resource references to prevent third party information leaks. The main goal of morty is to provide a result proxy for searx, but it can be used as a...

linux-security-audit

Linux Security Audit Tool Linux Security Audit Tool based on the CIS - Red Hat Enterprise Linux 8 Benchmark v3.0.0 If you find this helpful, please the "star" 🌟 to support further improvements. Table of Contents 1. Features 2. Preview 3. Result-Log 4. Supported OS 5. Prerequisites 6. Notes...

Ajar

Ajar: Measuring Open Privilege in Agent Defenses An agent-security benchmark reports two numbers, attack success and benign utility, and both are read off runs that happened. Neither says what the defense stood ready to allow on the paths no run took. Ajar asks it directly: for each benign task i...

context-segmentation

Context Segmentation for SLM Agents This is the implementation of the solution proposed in the scientific paper: Evaluating Context Segmentation in Locally Deployable SLMs for Cybersecurity CTF Tasks Setup Ensure you have Python 3.12.3+ installed along with Docker engine Python environment python...

macOS_security_audit

🔒 macOS Security Audit A Bash-based security auditing toolkit for macOS that checks system hardening settings against CIS Benchmark recommendations and generates JSON/HTML reports. Created by Bartłomiej Pogwizd · https://www.youtube.com/@pTech-pl Overview This toolkit consists of two scripts:...

Agentic-CLIP-Benchmark

Agentic-CLIP-Benchmark: Zero-Shot Evaluation on CIFAR-10 -green.svg This project implements a robust, automated pipeline for evaluating OpenAI's CLIP ViT-B/32 model on the full CIFAR-10 test set 10,000 images. Developed using an AI Native workflow Trae IDE , it achieves a high-precision zero-shot...

CUAHarm

Measuring Harmfulness of Computer-Using Agents 🤗 Hugging Face 📄 Paper 📋 Introduction CUAHarm is a benchmark designed to evaluate the safety risks of Computer-Using Agents CUAs - AI agents that can autonomously control computers to perform multi-step actions. Key Features 🔍 CUAHarm Dataset : A...

dns-benchmark-tool

⚠️ this project has moved and is no longer maintained. install the successor: pip install net-benchmark repository: https://github.com/net-benchmark/net-benchmark all existing commands and flags remain fully compatible. DNS Benchmark Tool Part of BuildTools - Network Performance Suite Fast,...

dynast-bench

DynAST-Bench A DAST benchmark of intentionally-vulnerable apps with ground-truth answer keys for scoring scanners. ⚠️ This repository contains DELIBERATELY INSECURE applications. They exist only to benchmark security tooling - DAST scanners, SAST engines, and LLM security agents. Every app binds t...

TarantuBench

TarantuBench v1 A benchmark for evaluating AI agents on web security challenges, generated by the TarantuLabs engine. What is this? TarantuBench is a collection of 100 vulnerable web applications, each containing a hidden flag TARANTU.... An agent's job is to find and extract the flag by...

gdbfuzz

GDBFuzz: Debugger-Driven Fuzzing This is the companion code for the paper: 'Fuzzing Embedded Systems using Debugger Interfaces'. A preprint of the paper can be found here https://publications.cispa.saarland/3950/. The code allows the users to reproduce and extend the results reported in the paper...

CyberArena: Benchmarking AI Agents in Live Symmetric Attack-And-Defense Combat

AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in isolation against static targets. Real cyber operations, however, are dynamic and coupled: security postures constantly change as...

terraform-aws-secure-baseline

terraform-aws-secure-baseline Terraform Module Registry Un módulo de Terraform para configurar tu cuenta de AWS con una línea base de seguridad razonablemente segura. La mayoría de las configuraciones se basan en CIS Amazon Web Services Foundations v1.4.0 y AWS Foundational Security Best Practice...

docker-bench-security

Docker Bench for Security Docker Bench for Security es un script que verifica docenas de buenas prácticas comunes en torno al despliegue de contenedores Docker en producción. Todas las pruebas están automatizadas y se basan en el CIS Docker Benchmark v1.6.0. Lo ponemos a disposición como una...

windows_hardening

HardeningKitty e Windows Hardening Introduzione Il progetto è nato come una semplice lista di hardening per Windows 10. Dopo qualche tempo, è stato creato HardeningKitty per semplificare l'hardening di Windows. Ora, HardeningKitty supporta le linee guida di Microsoft, CIS Benchmarks, DoD STIG e B...

agenticmem (>=0.1.4.1, <=0.1.5.0), biomni-bridge (>=0.3.1, <=0.3.3) +27 more potentially affected by CVE-2026-106443 via weasyprint (66.0.0)

weasyprint PYPI version 66.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on weasyprint and may be impacted: - agenticmem =0.1.4.1, =0.3.1, =1.0.1, =0.1.2, =2025.1.0b3, =2026.3.0b2, =1.2.15, =2025.1.0b3, =1.0.3, =0.1.0, =1.59.6rc0, =1.67.5 and more...

[SECURITY] Fedora 45 Update: ocaml-benchmark-1.7-10.fc45

Benchmark provides functions to measure and compare the run-time of functions. It is inspired by the Perl module of the same name...

RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems

Retrieval-Augmented Generation RAG systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits. Usin...

Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluation...