Supply Chain Attack Targets PyPI with Malicious AI-Inspired Packages

November 22, 2024

Supply Chain Attack Targets PyPI with Malicious AI-Inspired Packages

In an alarming development, Kaspersky’s Global Research and Analysis Team (GReAT) has uncovered a sophisticated supply chain attack that specifically targeted the Python Package Index (PyPI). This attack cleverly used malicious packages named ‘gptplus’ and ‘claudeai-eng’, which were designed to be mistaken for legitimate tools related to popular AI chatbot models like ChatGPT and Claude. By posing as useful utilities for these widely recognized AI platforms, the attackers aimed to deceive developers into downloading and using these compromised packages. Uploaded in November 2023, these malicious packages demonstrated seemingly legitimate functionalities, such as the ability to create chats and send messages to the language models, further aiding in their disguise.

As soon as these packages were imported, they activated a hidden process that executed Base64-encoded data. This process then downloaded a JavaUpdater.jar file from a GitHub repository. Within this file lay JarkaStealer, a powerful malware designed to harvest a wide array of data from compromised systems. Among the stolen information were browser data, screenshots, system information, and session data from applications like Telegram, Discord, and Steam. The deceptive packages managed to infiltrate over 1,700 systems across more than 30 countries. The highest download activity was observed in the United States, China, France, Germany, and Russia, highlighting the global reach and potential impact of this attack. Notably, the attackers did not appear to have any specific targets, making the attack even more concerning due to its indiscriminate nature.

Broader Implications and Continued Vigilance

Kaspersky’s Global Research and Analysis Team (GReAT) has discovered a sophisticated supply chain attack aimed at the Python Package Index (PyPI). Malicious packages named ‘gptplus’ and ‘claudeai-eng,’ designed to mimic legitimate tools linked to popular AI chatbots ChatGPT and Claude, were uploaded in November 2023. The attackers intended to deceive developers into downloading these compromised packages by making them appear as useful utilities.

Once imported, these packages began a hidden process that executed Base64-encoded data, subsequently downloading a JavaUpdater.jar file from a GitHub repository. This file contained JarkaStealer, potent malware designed to steal a wide range of data from affected systems. The data harvested included browser data, screenshots, system information, and session data from applications such as Telegram, Discord, and Steam.

These deceptive packages infiltrated over 1,700 systems in more than 30 countries, with the highest download activity in the United States, China, France, Germany, and Russia. The attack’s indiscriminate nature is particularly worrisome, as it targets no specific individuals or organizations, underscoring the potential global impact and reach of this threat.

Explore more

Is Desktop Customization the Cure for Linux Distro Hopping?

July 31, 2026

The rapid advancement of personal computing technology often creates a paradox where perfectly functional hardware is rendered obsolete by the arbitrary software constraints of major operating system vendors. Many users find themselves in a position where reliable machines, still possessing significant processing power and memory capacity, are suddenly excluded from receiving the latest security updates or feature sets. This forced

North Korean Hackers Use Fake macOS Updates to Steal Crypto

July 31, 2026

The sophisticated digital landscape of 2026 has witnessed a dramatic surge in highly targeted cyberattacks that specifically exploit the perceived inherent security of Apple’s macOS ecosystem. While many users once believed that the Unix-based architecture and rigorous app-vetting processes provided an impenetrable shield, state-sponsored actors from North Korea have proven otherwise by deploying deceptive software updates. These campaigns often leverage

Microsoft Copilot Flaw Enables Self-Propagating AI Worms

July 31, 2026

The rapid deployment of artificial intelligence within the corporate workspace has traditionally been viewed as a productivity catalyst, yet recent security discoveries have unveiled a sophisticated threat that fundamentally challenges the safety of automated workflows. Security researchers have identified a critical vulnerability within Microsoft Copilot for Word that facilitates a new class of “prompt injection” attacks, allowing malicious actors to

Is Your B2B PR Strategy Building Credibility or Just Noise?

July 31, 2026

Waiting until a major funding round or a massive product launch to initiate a public relations strategy often leaves B2B startups in a precarious position of anonymity during their most critical growth phases. Many founders operate under the misconception that public relations is a reactive mechanism, a lever to be pulled only when there is substantial news to share with

How Can B2B Brands Break Through Digital Marketing Fatigue?

July 31, 2026

The modern B2B procurement environment has transitioned into a hyper-saturated ecosystem where senior decision-makers are currently bombarded by a relentless stream of algorithmically generated outreach and automated marketing sequences. This pervasive digital marketing fatigue has rendered traditional tactics, such as high-volume email sequences and generic personalization tokens, largely ineffective for capturing the attention of high-value prospects who have grown cynical