Friday , July 10 2026
Villager

AI Pentesting Tool ‘Villager’ Merges Kali Linux with DeepSeek AI for Automated Attacks

The Villager framework, an AI-powered penetration testing tool, integrates Kali Linux tools with DeepSeek AI to automate cyber attack processes. Developed by the Chinese group Cyberspike, it was released on the Python Package Index in July 2025 and quickly gained over 10,000 downloads in two months.

Villager marks a major change in cybersecurity, with experts cautioning that it may turn into a tool for cybercriminals like Cobalt Strike did.

How Hacker Compromise AWS Cloud Environment Using AI in 72 Hours

A major AWS attack shows how attackers with AI can connect known cloud strategies to go from first access to...
Read More
How Hacker Compromise AWS Cloud Environment Using AI in 72 Hours

Mycelium Framework: First AI-as-a-Service Botnet

A new cybercrime ad is catching attention in the security world. It talks about a botnet that doesn't just get...
Read More
Mycelium Framework: First AI-as-a-Service Botnet

CrowdStrike Shows 5 New Prompt Injection Techniques for AI Agents

CrowdStrike has shared five new ways to inject prompts, showing the rising danger to AI agents as more organizations use...
Read More
CrowdStrike Shows 5 New Prompt Injection Techniques for AI Agents

Critical GCP Dialogflow Vulnerability Allows Malicious Code Injection

A critical flaw in Google Cloud Platform’s Dialogflow CX lets attackers add harmful code to a company's AI chatbot system....
Read More
Critical GCP Dialogflow Vulnerability Allows Malicious Code Injection

CIRT identified 153 publicly exposed FortiGate devices in Bangladesh

CIRT identified 153 publicly exposed FortiGate devices in Bangladesh. In an advisory CIRT said, the campaign has been observed globally,...
Read More
CIRT identified 153 publicly exposed FortiGate devices in Bangladesh

Thousands of MCP Servers Exposed to File Access and Injection Attacks

Thousands of Model Context Protocol (MCP) servers have serious security flaws like file access issues, command injection, server-side request forgery...
Read More
Thousands of MCP Servers Exposed to File Access and Injection Attacks

CERT/CC Alerts to Hidden Admin Backdoor in Tenda Router Firmware

Several Tenda firmware versions have a hidden backdoor that lets people gain admin access to the device's web interface. An...
Read More
CERT/CC Alerts to Hidden Admin Backdoor in Tenda Router Firmware

Daily Cyber security update for 6. 07. 2026

Cyberattacks are rising around the world, including ransomware, malware, data leaks, and hacked websites. These events show how complex and...
Read More
Daily Cyber security update for 6. 07. 2026

“Bad Epoll” 0-Day Vulnerability Allows Root Access on Linux Servers, Android Devices

A new Linux flaw called “Bad Epoll” (CVE-2026-46242) lets regular users get root access on Linux servers, desktops, and Android...
Read More
“Bad Epoll” 0-Day Vulnerability Allows Root Access on Linux Servers, Android Devices

An AI performed a cyber attack without any human help for the first time

Security experts found what they think is the first time an AI carried out a cyber attack all by itself....
Read More
An AI performed a cyber attack without any human help for the first time

Villager uses natural language processing to turn plain text commands into dynamic, AI-driven attack sequences, unlike traditional penetration testing frameworks that depend on scripted playbooks.

Villager functions as a Model Context Protocol (MCP) client, using a complex distributed system with various service components aimed at high automation and low detection.

The framework has key parts: an MCP Client Service on port 25989 for message coordination, a database with 4,201 AI prompts for improved decision-making, and automatic creation of isolated Kali Linux environments for network scanning and vulnerability assessment.

AI-powered Pentesting Tool ‘Villager’

This tool can avoid forensic detection by wiping activity logs every 24 hours and using random SSH ports, making analysis difficult. The temporary nature of attack containers and AI-driven orchestration makes it difficult for incident response teams to monitor malicious activity.

Villager’s integration with DeepSeek AI models occurs through custom API endpoints hosted at http://gpus.dev.cyberspike.top:8000/v1/chat/completions, utilizing a proprietary model designated “al-1s-20250421” with GPT-3.5-turbo tokenization.

This AI integration allows the framework to modify attack strategies based on system characteristics, automatically launching WPScan when it detects WordPress or switching to browser automation for API endpoints.

The Villager group, Cyberspike, registered their domain cyberspike[.]top on November 27, 2023. They are part of Changchun Anshanyuan Technology Co., Ltd., a Chinese firm specializing in AI and application software development.

However, investigations reveal concerning gaps in the company’s legitimacy, with no official website available and minimal business traces discoverable through standard corporate databases, Straiker said.

Archived website snapshots show that Cyberspike once sold a product suite with Remote Administration Tool (RAT) features. Version 1.1.7, released in December 2023, included a “built-in reverse proxy” and “multi-stage generator.”

The entire Cyberspike toolset was essentially a modified version of AsyncRAT, a popular Remote Access Trojan that cybercriminals have widely used since its 2019 GitHub release.

The developer of Villager is @stupidfish001, a former CTF player from the Chinese HSCSEC Team who has several email addresses. Click here to read the full report.

Check Also

Dialogflow

Critical GCP Dialogflow Vulnerability Allows Malicious Code Injection

A critical flaw in Google Cloud Platform’s Dialogflow CX lets attackers add harmful code to …