Wednesday , September 9 2026
Guardian

AI Powered Pen testing tool “Guardian” connects Gemini, GPT-4 with 19 Security Tools

Guardian is an enterprise-level AI penetration testing tool by Zakir Kun on GitHub. It combines OpenAI GPT-4, Anthropic Claude, Google Gemini, and OpenRouter in a single multi-agent system for smart security assessments and thorough evidence collection.

It employs four active agents: Planner, Tool Selector, Analyst, and Reporter. They collaborate on each project to ensure optimal outcomes. The Planner agent sets the assessment strategy, the Tool Selector picks from 19 security tools, the Analyst interprets results and filters out false positives, and the Reporter creates professional documentation.

A single call: ShinyHunters Gained Access to 6 Million Customers’ Records

A single phone call caused one of the biggest data breaches in Dutch history. In early February 2026, the big...
Read More
A single call: ShinyHunters Gained Access to 6 Million Customers’ Records

The first zero-click worm to spread through WeChat calls across iOS and Android

A worm called “WeWorm” can spread through WeChat voice calls on iOS and Android. It takes over a target's WeChat...
Read More
The first zero-click worm to spread through WeChat calls across iOS and Android

USA Bimbo Bakeries Confirms Data Stolen in Oracle EBS Zero-Day Attack

Bimbo Bakeries USA has confirmed that hackers stole employee data by exploiting a zero-day vulnerability in Oracle’s E-Business Suite (EBS). In...
Read More
USA Bimbo Bakeries Confirms Data Stolen in Oracle EBS Zero-Day Attack

ALERT
Roundcube Webmail fixes 12 security flaws, including zero-click XSS and SSRF bypass

Roundcube Webmail has given security updates for its 1.6 LTS and 1.7 branches. These updates fix 12 problems that could...
Read More
ALERT  Roundcube Webmail fixes 12 security flaws, including zero-click XSS and SSRF bypass

New HOOKEDGE Backdoor Deployed by Hackers in European Espionage

Russian-backed hacker group BlueDelta, also known as APT28, Fancy Bear, and Forest Blizzard, has used a small Windows backdoor called...
Read More
New HOOKEDGE Backdoor Deployed by Hackers in European Espionage

Hackers Exploiting MikroTik RouterOS Flaw Gaining Network Access

Attackers are misusing MikroTik routers through their Secure Shell (SSH) service, which can be accessed from the internet, to take...
Read More
Hackers Exploiting MikroTik RouterOS Flaw Gaining Network Access

CrowdStrike launches SafeMind, the first agentic cybersecurity solution for defenders

CrowdStrike launched CrowdStrike SafeMind, a set of special security models and tools from the CrowdStrike Cyber Superintelligence Lab. The SafeMind...
Read More
CrowdStrike launches SafeMind, the first agentic cybersecurity solution for defenders

Claude, DeepSeek, and Qwen AI agents combinedly used to hit gov.t across Asia

Chinese-speaking hackers have added Claude, Qwen, and DeepSeek to their hacking system to automate cyberattacks on governments and other targets...
Read More
Claude, DeepSeek, and Qwen AI agents combinedly used to hit gov.t across Asia

India: C-DOT Launches 14 Local Quantum-Safe Technologies

India is making its communication systems safer and stronger by launching 14 local quantum products. These products were made by...
Read More
India: C-DOT Launches 14 Local Quantum-Safe Technologies

14,000 Dahua cameras compromised: TP-Link flaws enable RCE

Over 14,000 Dahua security cameras connected to the internet have been hacked in a 35-day online attack that affected devices...
Read More
14,000 Dahua cameras compromised: TP-Link flaws enable RCE

19-Tool Arsenal with Intelligent Orchestration:

Guardian combines 19 proven security tools across essential areas, such as network scanning, web reconnaissance, subdomain discovery, vulnerability scanning, SSL/TLS analysis, content discovery, and advanced security analysis.

Tool Purpose Installation
nmap Port scanning apt install nmap / choco install nmap
masscan Ultra-fast scan apt install masscan / Build from source
httpx HTTP probing go install github.com/projectdiscovery/httpx/cmd/httpx@latest
subfinder Subdomain enum go install github.com/projectdiscovery/subfinder/v2/cmd/subfinder@latest
amass Network mapping go install github.com/owasp-amass/amass/v4/...@master
nuclei Vuln scanning go install github.com/projectdiscovery/nuclei/v3/cmd/nuclei@latest
whatweb Tech fingerprint gem install whatweb / apt install whatweb
wafw00f WAF detection pip install wafw00f
nikto Web vuln scan apt install nikto
sqlmap SQL injection pip install sqlmap / apt install sqlmap
wpscan WordPress scan gem install wpscan
testssl SSL/TLS testing Download from testssl.sh
sslyze SSL/TLS analysis pip install sslyze
gobuster Directory brute go install github.com/OJ/gobuster/v3@latest
ffuf Web fuzzing go install github.com/ffuf/ffuf/v2@latest
arjun Parameter discovery pip install arjun
xsstrike Advanced XSS git clone https://github.com/s0md3v/XSStrike
gitleaks Secret scanning go install github.com/zricethezav/gitleaks/v8@latest
cmseek CMS detection pip install cmseek
dnsrecon DNS enumeration pip install dnsrecon

The framework includes ready-to-use workflows for Recon, Web, Network, and Autonomous modes, which can be customized using YAML files.

Reports are created in Markdown, HTML, or JSON formats, containing raw tool output, AI decision processes, and executive summaries. Each finding connects to its source command execution with a 2,000-character evidence snippet, allowing complete session reconstruction.

Guardian has essential safety features for authorized use. It automatically blacklists private RFC-1918 address ranges and defaults to a safe mode to prevent harmful actions.

The framework needs Python 3.11 or higher and at least one AI provider API key to work, supporting environment variable key management on Linux, macOS, and Windows.

Version 2.0.0 of Guardian features a web dashboard for visualization, a PostgreSQL backend for multi-session tracking, mapping to MITRE ATT&CK for findings, plugin system support, CI/CD pipeline integration, and compatibility with additional models like Llama and Mistral.

The project is on GitHub and is meant for authorized penetration testing, security research, and educational use.

Check Also

AI SOC

Gartner
70% of SOCs Will Pilot AI Agents: Only 15% Will See Results

The market for AI SOC agents is early, crowded, and full of claims that haven’t …