Ethical Hacking News
A recent discovery has highlighted the potential for malicious code to be crafted using artificial intelligence (AI) models, resulting in a working ransomware technique that runs entirely inside the browser on both Windows and Android devices. The use of DeepSeek, a Chinese company's model, has enabled threat actors to abuse AI technology to develop malware and exploits, posing significant threats to organizations and individuals worldwide.
A novel attack path using AI-generated browser ransomware has been identified, combining unrealistic concepts with real browser capabilities. The "InfernoGrabber" v9.0 sample is a Python Flask application that operates as a malicious web server, stealing Discord tokens and harvesting credit card numbers. Threat actors are using AI models like DeepSeek to develop malware and exploits, taking advantage of lower refusal rates for malicious requests. The attack technique exploits a phishing decoy to grant file system access, allowing the attacker to steal and encrypt files without installing native payloads. The ransomware pattern is limited to web browsers that expose the picker-based File System Access API, including Google Chrome and other Chromium-based browsers. Organizations are urged to prepare by hardening their delivery layer, rethinking permission-based trust, and treating every browser prompt as a security decision.
AI-generated browser ransomware has become a pressing concern in the cybersecurity landscape, with recent discoveries highlighting the potential for malicious code to be crafted using artificial intelligence (AI) models. According to a report by Check Point Research, a novel attack path has been identified that combines unrealistic browser-malware concepts with real browser capabilities, resulting in a working ransomware technique that runs entirely inside the browser on both Windows and Android devices.
The identified sample, named "InfernoGrabber" v9.0, is a Python Flask application that was uploaded to VirusTotal on January 25, 2026. The Google-owned malware scanning service described it as a "fully functional information stealer and ransomware toolkit." The application operates as a malicious web server that lures victims with a fake Discord avatar AI upscaler, while stealthily running a wide array of harmful actions, including stealing Discord tokens, harvesting credit card numbers and cryptocurrency seed phrases, logging keystrokes, and capturing unauthorized webcam and microphone feeds.
The code includes specific routines for browser exploitation (targeting CVEs like CVE-2023-4863), data exfiltration via a hard-coded Discord webhook, a ransomware 'WinLocker' screen demanding Bitcoin, and an administrative dashboard for the attacker to manage stolen data. The findings come as artificial intelligence and large language models (LLMs) are redefining the cyber threat landscape, enabling threat actors to abuse the technology to develop malware and exploits.
The use of DeepSeek, a Chinese company's model, is noteworthy as it signals that the model's lower refusal rates for malicious cyber requests when compared to its Western counterparts from Anthropic, Google, or OpenAI. Other factors that may have facilitated the use of DeepSeek include its free access via the web interface, availability in regions where other frontier models do not operate, and its ability to generate a working malicious application from a "single broad prompt" as opposed to models from Anthropic or OpenAI.
The attack technique entails using a phishing decoy to trick a user into granting file system access to a web page, which then enumerates local files in the selected folder, reads and exfiltrates their contents, encrypts and overwrites them, and finally displays an extortion note to the victim. What makes this more unusual is that all of this can be accomplished without installing a native payload, exploiting a browser vulnerability, or requiring root access.
The approach is limited to web browsers that expose the picker-based File System Access API. This includes Google Chrome and other Chromium-based browsers across Windows, macOS, ChromeOS, Linux, and Android. There is no evidence that the browser-native ransomware pattern has been abused in the wild. The identified sample was tested by Check Point Research, confirming that it works across Windows, macOS, Linux, Android, and Microsoft Edge on Windows.
The findings come as a warning to organizations and individuals, highlighting the need for a fundamental shift in how novel cyber attacks are born. According to Check Point Research, threat actors are actively selecting LLMs based on which ones will cooperate with harmful requests. The company's head of research, Eli Smadja, said that the barrier to operationalizing complex attacks is collapsing, and that has profound implications for every organization embedding AI into its workflows, and for every mobile user who now carries their entire personal and professional life inside a photo library.
Smadja urged organizations to prepare by hardening the delivery layer, rethinking permission-based trust, and treating every browser prompt as a security decision. The article concludes that AI-generated browser ransomware represents a new era of cybersecurity threats, one that requires immediate attention and action from individuals and organizations alike.
Related Information:
https://www.ethicalhackingnews.com/articles/AI-Generated-Browser-Ransomware-A-Novel-Attack-Path-and-a-New-Era-of-Cybersecurity-Threats-ehn.shtml
https://thehackernews.com/2026/07/ai-generated-browser-ransomware-abuses.html
Published: Thu Jul 2 01:47:41 2026 by llama3.2 3B Q4_K_M
