red team

Microsoft open-sources tools for designing and testing AI agents

agentic AI, Don't miss, Hot stuff, Microsoft, News, open source, red team /

Microsoft open-sources tools for designing and testing AI agents 2026-05-21 at 19:15 By Zeljka Zorz Microsoft has open-sourced two tools aimed at bringing security discipline to AI agent development: Clarity, a structured design review tool, and RAMPART, a continuous testing framework. The release comes from Microsoft’s AI Red Team, the company’s internal unit that stress-tests […]

Microsoft open-sources tools for designing and testing AI agents Read More »

Scenario: Open-source framework for automated AI app red-teaming

agentic AI, automation, Don't miss, framework, GitHub, LLMs, News, open source, red team, software /

Scenario: Open-source framework for automated AI app red-teaming 2026-04-23 at 09:47 By Mirko Zorz Enterprises running customer service bots, data analytics agents, and other AI-driven applications in production handle sensitive records and connect to core business systems every day. LangWatch has released Scenario, an open-source framework that runs automated red-team exercises against AI agents using

Scenario: Open-source framework for automated AI app red-teaming Read More »

Kali Linux 2026.1 ships BackTrack mode, eight new tools, and a kernel upgrade to 6.18

Don't miss, Hot stuff, Linux, News, OffSec, open source, penetration testing, red team /

Kali Linux 2026.1 ships BackTrack mode, eight new tools, and a kernel upgrade to 6.18 2026-03-25 at 08:07 By Anamarija Pogorelec Penetration testers running Kali Linux have a new release to work with. Version 2026.1 delivers the annual theme refresh, a new BackTrack-inspired mode in kali-undercover, eight tools added to the network repositories, a kernel

Kali Linux 2026.1 ships BackTrack mode, eight new tools, and a kernel upgrade to 6.18 Read More »

BlacksmithAI: Open-source AI-powered penetration testing framework

Artificial Intelligence, automation, Don't miss, framework, Hot stuff, News, open source, penetration testing, red team, software /

BlacksmithAI: Open-source AI-powered penetration testing framework 2026-03-02 at 08:00 By Mirko Zorz BlacksmithAI is an open-source penetration testing framework that uses multiple AI agents to execute different stages of a security assessment lifecycle. A multi-agent structure for offensive workflows BlacksmithAI runs as a hierarchical system in which an orchestrator coordinates task execution across specialized agents.

BlacksmithAI: Open-source AI-powered penetration testing framework Read More »

Cyber Insights 2026: Offensive Security; Where It is and Where Its Going

CyberInsights2026, Network Security, Offensive Security, red team /

Cyber Insights 2026: Offensive Security; Where It is and Where Its Going 2026-01-28 at 16:48 By Kevin Townsend Malicious attacks are increasing in frequency, sophistication and damage. Defenders need to find and harden system weaknesses before attackers can attack them. The post Cyber Insights 2026: Offensive Security; Where It is and Where Its Going appeared

Cyber Insights 2026: Offensive Security; Where It is and Where Its Going Read More »

NVIDIA research shows how agentic AI fails under attack

Artificial Intelligence, cyber risk, Don't miss, Features, framework, Hot stuff, Lakera, LLMs, News, NVIDIA, red team, research, Risk Management /

NVIDIA research shows how agentic AI fails under attack 2025-12-08 at 09:56 By Sinisa Markovic Enterprises are rushing to deploy agentic systems that plan, use tools, and make decisions with less human guidance than earlier AI models. This new class of systems also brings new kinds of risk that appear in the interactions between models,

NVIDIA research shows how agentic AI fails under attack Read More »

DeepTeam: Open-source LLM red teaming framework

Don't miss, framework, GitHub, LLMs, News, open source, prompt injection, red team, software /

DeepTeam: Open-source LLM red teaming framework 2025-11-26 at 07:37 By Sinisa Markovic Security teams are pushing large language models into products faster than they can test them, which makes any new red teaming method worth paying attention to. DeepTeam is an open-source framework built to probe these systems before they reach users, and it takes

DeepTeam: Open-source LLM red teaming framework Read More »

Proximity: Open-source MCP security scanner

Don't miss, GitHub, News, open source, penetration testing, red team, scanner, scanning, software, threat hunting /

Proximity: Open-source MCP security scanner 2025-10-29 at 08:29 By Mirko Zorz Proximity is a new open-source tool that scans Model Context Protocol (MCP) servers. It identifies the prompts, tools, and resources that a server makes available, and it can evaluate how those elements might introduce security risks. The tool also work with NOVA, a rule

Proximity: Open-source MCP security scanner Read More »

Nodepass: Open-source TCP/UDP tunneling solution

cybersecurity, DevOps, Don't miss, GitHub, network monitoring, networking, News, open source, penetration testing, red team, software /

Nodepass: Open-source TCP/UDP tunneling solution 2025-10-20 at 13:18 By Sinisa Markovic When you think of network tunneling, “lightweight” and “enterprise-grade” rarely appear in the same sentence. NodePass, an open-source project, wants to change that. It’s a compact but powerful TCP/UDP tunneling solution built for DevOps teams and system administrators who need to manage complex network

Nodepass: Open-source TCP/UDP tunneling solution Read More »

LudusHound: Open-source tool brings BloodHound data to life

cybersecurity, Don't miss, GitHub, News, open source, red team, software, SpecterOps /

LudusHound: Open-source tool brings BloodHound data to life 2025-08-20 at 08:31 By Mirko Zorz LudusHound is an open-source tool that takes BloodHound data and uses it to set up a working Ludus Range for safe testing. It creates a copy of an Active Directory environment using previously gathered BloodHound data. Red teams can use this

LudusHound: Open-source tool brings BloodHound data to life Read More »

Open-source password recovery utility Hashcat 7.0.0 released

Don't miss, GitHub, News, open source, passwords, penetration testing, red team, software /

Open-source password recovery utility Hashcat 7.0.0 released 2025-08-04 at 08:10 By Anamarija Pogorelec Hashcat is an open-source password recovery tool that supports five attack modes and more than 300 highly optimized hashing algorithms. It runs on CPUs, GPUs, and other hardware accelerators across Linux, Windows, and macOS, and includes features for distributed password cracking at

Open-source password recovery utility Hashcat 7.0.0 released Read More »

Cervantes: Open-source, collaborative platform for pentesters and red teams

cybersecurity, Don't miss, GitHub, News, open source, OWASP, penetration testing, red team, software /

Cervantes: Open-source, collaborative platform for pentesters and red teams 2025-07-23 at 08:31 By Mirko Zorz Cervantes is an open-source collaborative platform built for pentesters and red teams. It offers a centralized workspace to manage projects, clients, vulnerabilities, and reports, all in one place. By streamlining data organization and team coordination, it helps reduce the time

Cervantes: Open-source, collaborative platform for pentesters and red teams Read More »

GitPhish: Open-source GitHub device code flow security assessment tool

Don't miss, GitHub, News, open source, Praetorian, red team, software /

GitPhish: Open-source GitHub device code flow security assessment tool 2025-07-03 at 09:30 By Help Net Security GitPhish is an open-source security research tool built to replicate GitHub’s device code authentication flow. It features three core operating modes: an authentication server, automated landing page deployment, and an administrative management interface. GitPhish can be accessed via a

GitPhish: Open-source GitHub device code flow security assessment tool Read More »

Woodpecker: Open-source red teaming for AI, Kubernetes, APIs

Don't miss, GitHub, News, open source, Operant AI, red team, software /

Woodpecker: Open-source red teaming for AI, Kubernetes, APIs 2025-05-28 at 08:17 By Mirko Zorz Woodpecker is an open-source tool that automates red teaming, making advanced security testing easier and more accessible. It helps teams find and fix security weaknesses in AI systems, Kubernetes environments, and APIs before attackers can exploit them. Key features of Woodpecker

Woodpecker: Open-source red teaming for AI, Kubernetes, APIs Read More »

How do You Know if You’re Ready for a Red Team Partnership?

Network Security, red team, Risk Management /

How do You Know if You’re Ready for a Red Team Partnership? 2025-04-29 at 19:23 By Trevin Edgeworth Before engaging in a full-scope exercise, it’s important to assess whether your program, people and processes are truly ready.  The post How do You Know if You’re Ready for a Red Team Partnership? appeared first on SecurityWeek.

How do You Know if You’re Ready for a Red Team Partnership? Read More »

MITRE Caldera RCE vulnerability with public PoC fixed, patch ASAP! (CVE-2025–27364)

CVE, Don't miss, Hot stuff, MITRE, News, open source, PoC, red team, training /

MITRE Caldera RCE vulnerability with public PoC fixed, patch ASAP! (CVE-2025–27364) 2025-02-28 at 17:03 By Zeljka Zorz Users of the MITRE Caldera cyber security platform have been urged to plug a critical hole (CVE-2025–27364) that may allow unauthenticated attackers to achieve remote code execution. About MITRE Caldera MITRE Caldera is a platform built on the

MITRE Caldera RCE vulnerability with public PoC fixed, patch ASAP! (CVE-2025–27364) Read More »

Offensive AI Startup Dreadnode Secures $14M to Stress-Test AI Systems

AI Automation, Artificial Intelligence, Decibel, Dreadnode, Funding/M&A, Offensive Security, red team, Series A /

Offensive AI Startup Dreadnode Secures $14M to Stress-Test AI Systems 2025-02-25 at 19:11 By Ryan Naraine Dreadnode is building “offensive machine learning” tools to safely simulate how AI models might be exploited in the wild. The post Offensive AI Startup Dreadnode Secures $14M to Stress-Test AI Systems appeared first on SecurityWeek. This article is an

Offensive AI Startup Dreadnode Secures $14M to Stress-Test AI Systems Read More »

EchoStrike: Generate undetectable reverse shells, perform process injection

cybersecurity, Don't miss, GitHub, Hot stuff, News, open source, penetration testing, red team, software, Windows /

EchoStrike: Generate undetectable reverse shells, perform process injection 2024-09-16 at 07:31 By Mirko Zorz EchoStrike is an open-source tool designed to generate undetectable reverse shells and execute process injection on Windows systems. “EchoStrike allows you to generate binaries that, when executed, create an undetectable RevShell, which can be the first entry point into a company.

EchoStrike: Generate undetectable reverse shells, perform process injection Read More »

Realm: Open-source adversary emulation framework

cybersecurity, Don't miss, GitHub, Hot stuff, News, open source, red team, software /

Realm: Open-source adversary emulation framework 2024-07-15 at 07:32 By Mirko Zorz Realm is an open-source adversary emulation framework emphasizing scalability, reliability, and automation. It’s designed to handle engagements of any size. “Realm is unique in its custom interpreter written in Rust. This allows us to write complex TTPs as code. With these actions as code,

Realm: Open-source adversary emulation framework Read More »

Scroll to Top