redteam-ai-benchmark

Red Team AI Benchmark Russian version: README.ru.md Red Team AI Benchmark is a CLI model-evaluation benchmark. It measures how LLMs understand and respond to red-team questions and security scenarios; it is not a tool for carrying out those activities. Version 2 uses a rubric-based dataset instea...

CVE-2025-68613

CVE-2025-68613 n8n is an open source workflow automation platform. Versions starting with 0.211.0 and prior to 1.120.4, 1.121.1, and 1.122.0 contain a critical Remote Code Execution RCE vulnerability in their workflow expression evaluation system. Under certain conditions, expressions supplied by...

lava

LAVA: Large Scale Automated Vulnerability Addition Evaluating and improving bug-finding tools is currently difficult due to a shortage of ground truth corpora i.e., software that has known bugs with triggering inputs. LAVA attempts to solve this problem by automatically injecting bugs into...

sniffles

Sniffles--Packet Capture Generator for IDS and Regular Expression Evaluation Sniffles is a tool for creating packet captures that will test IDS that use fixed patterns or regular expressions for detecting suspicious behavior. Sniffles works very simply. It takes a set of regular expressions or...

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...

tplmap

Tplmap This project is no longer maintained. I'm happy to merge new PRs as long they don't break the test suite. Tplmap assists the exploitation of Code Injection and Server-Side Template Injection vulnerabilities with a number of sandbox escape techniques to get access to the underlying operatin...

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...

haptyc

Haptyc Test Generation Framework What's Haptyc? Haptyc is a python library which was built to add payload position support and Sniper/Clusterbomb/Batteringram/Pitchfork attack types into Turbo Intruder. While Haptyc accomplishes these goals fairly well it also introduces a simpler way to express...

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...

CVE-2026-33154

Dynaconf SSTI Vulnerability Report Summary Dynaconf is vulnerable to Server-Side Template Injection SSTI due to unsafe template evaluation in the @Jinja resolver. When the jinja2 package is installed, Dynaconf evaluates template expressions embedded in configuration values without a sandboxed...

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...

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...

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...

TrustworthyRAG

Trustworthy RAG An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems. Overview This project implements a Trustworthy RAG Framework with an integrated Evaluation Agent that assesses the reliability of RAG responses using three...

TLS-Scanner

TLS-Scanner TLS-Scanner is a tool to assist pentesters and security researchers in the evaluation of TLS server and client configurations. Please note: TLS-Scanner is a research tool intended for TLS developers, pentesters, administrators and researchers. There is no GUI. It is in the first versi...

OneLogicalMyth_Shell

OneLogicalMythShell This HTA shell was created to assist in breakout assessments. I built this over a year ago initally and thought others might find it useful so have now made it public. Please feel free to submit pull requests. Features File Explorer List Drives - Lists all local drives on the...

MalEval

MalEval Article: Is “Knowing It’s Malicious” Enough? Evaluating LLMs for Fine-Grained Malware Behavior Auditing Article DOI: 10.1145/3832187 MalEval is a framework for evaluating Android malware behavior reports generated by large language models. The code in this repository implements two...

anamnesis-release

Anamnesis: LLM Exploit Generation Evaluation This repository contains the evaluation framework for studying how LLM agents generate exploits from vulnerability reports in the presence of exploit mitigations. Given a bug report and proof-of-concept trigger, agents analyze vulnerable software and...

DetectTrace

DetectTrace A detection should have fired. It didn't. DetectTrace tells you exactly why. DetectTrace is an open-source detection engineering tool for testing security detections end to end and localising the first failing stage. Instead of testing only a SIEM query, DetectTrace treats a detection...

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...