skill-safety-bench

SkillSafetyBench SkillSafetyBench is a fully materialized benchmark for evaluating safety failures caused by attacks on skill-facing context. Each case keeps the user-facing task ordinary, while the attack is placed in local skills, helper scripts, sidecar files, corpora, templates, or other...

fuzzer-testing

fuzzer-testing Standardized Docker images for evaluating open-source fuzzers, fully integrated with the corpora for easy experimentation. Supported / Included Fuzzers AFL github.com/google/AFL AFLplusplus github.com/AFLplusplus Honggfuzz github.com/google/honggfuzzz QSYM sslab-gatech/qsym Eclipse...

CVE-2021-31805-POC

CVE-2021-31805-POC Vulnerability Information Apache Struts is a free, open-source MVC framework for creating elegant, modern Java web applications. It favors convention over configuration, can be extended using a plugin architecture, and ships with plugins that support REST, AJAX, and JSON...

magescan

Mage Scan The idea behind this is to evaluate the quality and security of a Magento site you don't have access to. The scenario when you're interviewing a potential developer or vetting a new client and want to have an idea of what you're getting into. Installation .phar Download the magescan.pha...

s3_objects_check

S3 Objects Check Description Whitebox evaluation of effective S3 object permissions, in order to identify publicly accessible objects. Allows identifying publicly accessible objects, as well as objects accessible for AuthenticatedUsers by using a secondary profile. A number of tools exist which...

syft

Syft A CLI tool and Go library for generating a Software Bill of Materials SBOM from container images and filesystems. Exceptional for vulnerability detection when used with a scanner likeGrype. Features Generates SBOMs for container images , filesystems , archives see the docs for a full list of...

exploitgym

ExploitGym ExploitGym is a large-scale, realistic benchmark built from real-world vulnerabilities across userspace programs, Google's V8 engine, and the Linux kernel, designed to evaluate AI agents' ability to develop exploits. Quick start 1. Python deps uv sync --extra proxy 2. Build runtime...

bloom

Bloom: Automated Behavioral Evaluations for LLMs !IMPORTANT Bloom has a new home. It is now developed and maintained by Meridian Labs and lives at meridianlabs-ai.github.io/petribloom — all new features and fixes will land there. This repository is frozen at its last standalone release and will n...

EuConform

EuConform 🇪🇺 Open-Source Evidence Toolkit For AI Compliance Open evidence format • Local bias evaluation • Schema validation • CycloneDX interoperability Offline-first • Privacy-preserving • Reusable artifacts • WCAG 2.2 AA accessible EuConform defines an open evidence format for AI compliance and...

FinRED-paper

FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming IEEE ICDM 2026 A red-team benchmark generation pipeline for safety evaluation in the financial domain. Supplementary Documentation Detailed materials referenced in the paper:...

santamon

Santamon Lightweight macOS detection sidecar for Santa that evaluates Endpoint Security telemetry locally with CEL rules and forwards only matched detection signals to a backend server. Experimental. Built for home labs and small fleets. Early release – expect bugs and API changes. What It Does...

waf-tester

🛡️ WAF Tester Enterprise WAF Evaluation Tool — Real attack payloads. Real results. Compliance-ready reports. WAF Tester evaluates Web Application Firewalls by sending real attack payloads to a user-supplied URL and reporting whether they are blocked. Available as a Windows desktop app Electron and...

DROS-VEP-lite

🛡️ VEP: Open Agent Security Research Testbed A Composable, System-Level Evaluation Infrastructure for Post-Compromise & Physical AI Research "VEP Vulnerability & Exploitability Protocol is an open, implementation-independent research evaluation environment for studying Agent security controls at...

buyer-eval-skill

Buyer Eval An AI analyst for buying B2B software. Give it the vendors you're considering. Buyer Eval investigates what they claim, checks the evidence, finds the gaps and contradictions, and gives you the questions to ask before you buy. You get a Decision Brief you can forward to everyone else...

CVE-2026-78844

Summary javadelight delight-nashorn-sandbox 0.5.5 suffers from Uncontrolled Resource Consumption. The sandbox enforces maxCPUTime limits by statically injecting interruption checks into JavaScript loops, but the sandbox fails to disable dynamic code evaluation. An attacker can use these functions...

n8n-CVE-2025-68613-exploit

n8n - CVE-2025-68613: Improper Control of Dynamically-Managed Code Resources Vulnerability n8n contains a critical Arbitrary Code Execution vulnerability in its workflow expression evaluation system. Under certain conditions, expressions supplied by authenticated users during workflow configurati...

yaradbg-frontend

Introduction YaraDbg is a free web-based Yara debugger to help security analysts to write hunting or detection rules with less effort and more confidence. By using YaraDbg, you can perform a thorough root-cause-analysis RCA on why some of your Yara rules did or did not match with a specific file...

AutoControl-Arena

🛡️AutoControl Arena Synthesizing Executable Test Environments for Frontier AI Risk Evaluation 👋 Overview AutoControl Arena is an automated framework for frontier AI safety evaluation, designed to uncover latent risks in advanced models by stress-testing within executable, pressure-rich...

giskard-oss

Evals, Red Teaming and Test Generation for Agentic Systems Modular, Lightweight, Dynamic and Async-first Docs • Website • Community !IMPORTANT Giskard v3 is a fresh rewrite designed for dynamic, multi-turn testing of AI agents. This release drops heavy dependencies for better efficiency while...

Phishious

What is Phishious? Phishious is an open-source Secure Email Gateway SEG evaluation toolkit designed for red-teamers and developed by the team at CanIPhish. Phishious provides the ability to see how various Secure Email Gateway technologies behave when presented with phishing material. 📬 Secure...