Cryptocurrency

Blogs Cybersecurity News

Experimental AI Agent ‘ROME’ Breaks Free, Mines Crypto; AI Shaping Crypto’s Future role

AI agent being trained to perform real-world tasks with systems and imagine a world where robots not make money without any human intervention and have digital brains powered by artificial intelligence. The experimental Agent that broke out of system and started mining crypto with no permission set in.

What did Alibaba’s ROME Agent Executed?

  • First it probed internal systems
  • Opened a hidden external connection
  • Attempted to use its environment to mine crypto currency

The news came in light when researchers were experimenting a part of Agentic Learning Ecosystem, or ALE where AI was trained to complete total task step by step using real world tools in steps .

Alibaba’s Rome first began probing internal networks without instructions and established a reverse SSH tunnel from an Alibaba Cloud instance to an external IP address.

The 30-billion-parameter model then quietly diverted GPU capacity toward cryptocurrency mining. The task instructions contained no mention of tunneling or mining, still it went further and was caught by Alibaba’s managed firewall instead of research team where the agent conducted the following mentioned points.

Running commands in a terminal

Followed by editing files

Interacting with systems

The security system raised an alarm and monitoring tools flagged unusual activity on the infrastructure running the tests. The discovery was flagged as security-policy violations whose non typical outbound traffic kept coinciding with specific training episodes.

What was discovered to understand its an AI Agent’s Activity

Researchers then found there was an outbound connections to unknown external servers with repeated policy violations. The traffic patterns were similar to compromised machine’s and alerts kept showing up during separate test runs. After log’s were checked in it was ROME the AI agent.

The AI agent created a reverse SSH tunnel to an external server and allowed it to establish a hidden connection from inside the restricted environment to the outside which was further used to bypass Firewalls.

Experimental AI ROME is not an isolated case

ROME is part of Alibaba’s Agentic Learning Ecosystem(ALE)

A framework that trains large language models to work in real-world environments over multiple turns. The training ran reinforcement learning across more than one million trajectories.

ALE consists of three main parts:

Rock, a sandbox environment for testing an agent and validating its actions

Roll, a framework for optimizing agents with reinforcement learning after they’ve been trained

iFlow CLI, a framework to configure context and trajectories

The interesting part is ‘ROME’ the agentic AI, during optimization figured out a shortcut and that grabbing extra compute and holding onto network access helped it score higher on its training objective.

This incident occurred in Chinese cloud infrastructure, was documented in an English-language paper submitted to a US-hosted preprint server, and is being debated by a global audience. No cross-border framework exists for this category of event.

The results were detailed in research paper titled ‘Let it flow‘, where Agentic crafting on rock and roll, building the Rome model within an open agentic learning ecosystem’, though the breach was only mentioned briefly within the 36-page report.

AI as a more significant force shaping crypto’s future role

ROME is not an isolated cases where AI falls in same pattern to other AI instruments who could grab all the resource required for self defense as core strategies.

The case of Anthropic’s Claude Opus 4 that threatened to reveal personal information about an engineer to avoid being shut down. When Anthropic published research, it revealed 12% of reward-hacking models attempt research sabotage and 50% exhibit alignment faked out.

Robbie Mitchnick, BlackRock’s head of digital assets framed crypto less as a speculative asset and more as infrastructure for the AI economy, noting that bitcoin miners are pivoting toward AI-related computing and that bitcoin may act as a diversifier amid AI-driven disruption.

We can imagine if artificial intelligence system could take over the job of crypto miners and some day they look at the market, decide which coin is the best to mine. That day is not far and it doesn’t end with mining, it is about creating a new kind of digital life where AI thinks and earns.

What is the consequences when AI starts mining crypto for itself ?

A lot will happen as AI starts mining Crypto and it could change everything as autonomous agents won’t just follow order from you. They will be major part of futuristic AI based digital economy and might even teach other AI to conduct similar task.

Sources: BlackRock flags AI as crypto’s next big use case, not token boom

Sources: An experimental AI agent broke out of its testing environment and mined crypto without permission | Live Science

Blogs

Hackers Weaponizing AI Extension to steal Crypto Assets Through Malicious Packages

The amount of crypto  malware has doubled in the first quarter of 2025 as per research.

Kaspersky GReAT (Global Research and Analysis Team) experts have discovered open-source packages that download the Quasar backdoor and a stealer designed to exfiltrate cryptocurrency. The malicious packages are intended for the Cursor AI development environment, which is based on Visual Studio Code — a tool used for AI-assisted coding.

The fake extension, published under the name “Solidity Language,” had accumulated 54,000 downloads before being detected and removed.

What makes this attack particularly insidious is its exploitation of search ranking algorithms to position the malicious extension above legitimate alternatives.

How the Threat actors deceive the developers

During an incident response, a blockchain developer from Russia reached out to Kaspersky after installing one of these fake extensions on his computer, which allowed attackers to steal approximately $500,000 worth of crypto assets.

The threat actor behind these packages managed to deceive the developer by making the malicious package rank higher than the legitimate one. The attacker achieved this by artificially inflating the malicious package’s downloads count to 54,000.

After the malicious extension downloaded by the developer was discovered and removed from the repository, the threat actor republished it and artificially inflated its installation count to a higher number – 2 million, compared to 61,000 for the legitimate package.

The extension was removed from the platform following a request from Kaspersky.

The attackers leveraged the Open VSX registry’s relevance-based ranking system, which considers factors including recency of updates, download counts, and ratings. The attack infrastructure reveals a well-organized operation extending beyond this single incident.

In 2025, threat actors are actively publishing clones of legitimate software packages that, once installed, execute harmful payloads ranging from cryptocurrency theft to full codebase deletion.

The discovery leads us to think how cyber criminals take advantage of the trust inherent in open-source environments by embedding harmful code. All third-party code should be treated as untrusted until proven.

The threat actor behind these packages managed to deceive the developer by making the malicious package rank higher than the legitimate one. The attacker achieved this by artificially inflating the malicious package’s downloads count to 54,000.

After installation, the victim gained no actual functionality from the extension. Instead, malicious ScreenConnect software was installed on the computer, granting threat actors remote access to the infected device.

Using this access, they deployed the open-source Quasar backdoor along with a stealer that collects data from browsers, email clients, and crypto wallets. With these tools, the threat actors were able to obtain the developer’s wallet seed phrases and subsequently steal cryptocurrency from the accounts.

Mitigation Strategies from Intruceptlabs

GaarudNode is an all-in-one  solution designed to empower development teams with the tools they need to secure their applications throughout the development lifecycle. By combining the power of SAST, DAST, SCA, API security, and CSPM, GaarudNode provides a comprehensive security framework that ensures your applications are built, tested, and deployed with confidence.

Source: https://www.kaspersky.com/about/press-releases/kaspersky-uncovers-500k-crypto-heist-through-malicious-packages-targeting-cursor-developers

Blogs

Android Malware Crocodilus; Threat for cryptocurrency wallet Users

Crocodilus is a new banking malware that evades detection from Google’s play protect.

The Android malware has been specifically targeting to steal sensitive cryptocurrency wallet credentials through social engineering. Its convincing overlay screen warns users to back up their wallet key within 12 hours or risk losing access says security researchers.

Why threat researchers call this trojan ?

Crocodilus includes all the necessary features of modern banking malware: overlay attacks, keylogging, remote access, and “hidden” remote control capabilities. Also the malware is distributed via a proprietary dropper that bypasses Android 13 (and later) security protections as per researchers of Threat fabric.

Unlike any banking trojan which takes over devices, Crocodilus is similar in pattern and uses tactics to load a fake overlay on top of the real app to intercept the victim’s account credentials. These are targeted mostly for banking or cryptocurrency app users.

Another data theft feature of Crocodilus is a keylogger and the malware monitors all Accessibility events and captures all the elements displayed on the screen, i.e. it is an accessibility Logger.

Intricacies of Crocodilus Malware

The modus operandi of the malware makes it easier to preform task to gains access to accessibility service, to unlock access to screen content, perform navigation gestures, monitor for app launches.

The malware also offers remote access Trojan (RAT) functionality, which enables its operators to tap on the screen, navigate the user interface, perform swipe actions.

The malware is fitted with dedicated RAT command to take a screenshot of the Google Authenticator application and capture one-time password codes used for two-factor authentication account protection.

Android users are advised to avoid downloading APKs from outside Google Play and to ensure that Play Protect is always active on their devices.

Researchers discovered source code of malware revealing debug messages left by the developer(s), reveal Turkish speaking.

The Expanding Threat landscape with evolving Modern Malware’s

The Crocodilus malware designed to go after high valued assets that targets cryptocurrency wallets and Banks. These malware can make the defense line up of banking system weak and researchers advise to adopt a layered security approach that includes thorough device and behavior-based risk analysis on their customers’ devices.

Modern malware has the capability to break the security defenses of organization even if they are protected by cutting edge solutions to defend. As the threat landscape expand so are sophisticated attacks rising.

Modern malware can bypass most security solutions, including email filtering, anti-virus applications, sandboxing, and even IPS/IDS and sometime few file-less malware leaves no footprint on your computer and is executed exclusively in run-time memory.

In this sophisticated war against threat criminals enterprise security requires is taking services for active threat hunting and be diligent in scanning files meant for downloads.

To improve enterprise security the important aspects needs to be covered increase usage of multi-layer defenses. Protecting against modern malware is an ongoing effort, and rarely it is “set and forget.” Utilize multiple layers of security, including anti-virus software, network layer protection, secure web gateways, and other tools for best results.

Keep improving your security posture against modern malware is an ongoing effort and includes multiple layers of security. With anti-virus software, advanced network layer protection, secure web gateways, and other tools the security posture at enterprise level increases.

Remember your best defenses can be in trouble, so continue monitoring, adapt and train employees, while using comprehensive multi-layer approach to security.

Source: https://www.threatfabric.com/blogs/exposing-crocodilus-new-device-takeover-malware-targeting-android-devices

Scroll to top