Malware that takes technical cues from a poem to assemble a growing botnet by targeting open-source AI services has compromised more than 3,400 servers since April, Lumen Technologies’ Black Lotus Labs said in a report Wednesday. 

The poem, which a threat actor wrote and posted on a GitHub repository, seems innocuous but it’s driving a stealthy piece of malware researchers call PoeLLM. Four specific words extracted from the poem, which have been changed at least a dozen times, are converted into a command-and-control server address through a hard-coded dictionary embedded in the malware — a framework that bolsters PoeLLM’s resiliency.

“The most interesting piece of the poem approach is that the IP address used for C2 communications is invisible outside of the victim’s netflow. In other malware samples, there might be a hard-coded fallback C2 address, or URL which points to an IP address written elsewhere on the internet,” Ryan English, information security engineer at Black Lotus Labs, told CyberScoop.

“To anyone who comes across it, this is simply a poem on GitHub. It has no links, no files to download, no encrypted text that could easily be flagged as malicious, even by advanced models,” he added. “There would be no reason for any security researcher to identify this poem as malicious — or know about the IP address hidden within it — unless they had access to the malware referencing it.”

Researchers first encountered PoeLLM infrastructure in June during an investigation into a maximum-severity defect affecting Ivanti’s secure mobile gateway product, Sentry. That discovery uncovered a sweeping exploit-scanning and cryptocurrency-mining botnet linked to multiple compromised services and tools, including LiteLLM, Ollama, Gotenberg and Gitea.

While “PoeLLM has been extremely successful in compromising multiple AI-related services at scale,” the threat actor’s achievements beyond exploit scanning and cryptomining remain under investigation, English said. 

The malware contains functionality that can allow for remote code execution, potentially allowing a threat actor to abuse AI models on victim servers, along with public-facing services for downstream compromise, he added.

“Through the growth of this botnet, the actor has effectively created a private army of AI-enabled proxies, which will continue to multiply and provide additional vectors for attack, credential theft, token abuse and more,” English said.

The botnet has continued to grow by converting compromised servers into attackers and shifting through C2 infrastructure, leaving fewer traces across the internet.

“If one exploit server gets reported by the security community, the attacker can easily pivot and start proxying attacks through hundreds of other compromised victims,” English said. 

The poem serves as a dynamic lookup table for this infrastructure rotation. When the malware retrieves the updated poem from GitHub, it extracts four specific words based on their positions relative to fixed text anchors within the verse. Each extracted word is then matched against a hard-coded dictionary in the malware, where individual words map to sets of IP addresses. The four numbers combine to form the current C2 server address. This means the threat actor can change the entire poem, and thus the C2 location, without updating the malware itself.

“Many of the C2s used in this campaign were never detected on crowd-sourced security tools, indicating that this layer of obfuscation was very helpful in improving the resilience of a C2,” English said.

For instance, the first stanza of the poem, as it was observed last month, reads: “In the silent hum of driver, the machines begin to speak, each pulse of diode threading light through copper veins. We taught the dark to carry meaning, byte by byte — a language built from lightning, cold and clean.”

The malware extracts four specific words from the poem and matches each to a number in a hard-coded dictionary — for example, “driver” equals 92, “diode” equals 119, “decryption” equals 165, and “string” equals 74, combining to form the C2 address. When the threat actor changes the poem’s keywords, the malware automatically calculates a new C2 address without needing to update itself. This keeps the infrastructure invisible to network monitoring tools unless the malware code is directly analyzed.

Black Lotus Labs said the threat actor behind PoeLLM is likely Italian or speaks Italian. Researchers observed multiple comments in the malware code written in Italian and said the threat actor has relied on Italy-based servers for testing and C2 infrastructure. 

Researchers said they don’t know how many people are involved in the PoeLLM’s operation, and they haven’t observed any connections to other groups or campaigns.

The post PoeLLM malware has assembled a sweeping botnet, taking technical cues from a poem appeared first on CyberScoop.

In less than four hours early Tuesday, an attacker compromised a GitHub maintainer account and unleashed a self-replicating piece of malware which injected malicious code into more than 440 distinct npm packages, according to multiple security firms. 

The worm, built on the open-source Mini Shai-Hulud repository that TeamPCP published in May, was initially let loose in keyv, a data management interface software package with more than 600 million monthly downloads. The attacker spent the next 30 minutes compromising additional packages controlled by the same maintainer, including cacheable, flat-cache, file-entry-cache.

The attack spread to other maintainers, eventually compromising more than 860 packages with a “combined total of over 2 billion monthly installs,” Ilyas Makari, malware researcher at Aikido Security, wrote in a blog post. 

Wiz researchers told CyberScoop it hasn’t observed any new malicious packages since the initial wave moved through a massive footpoint of cloud and code environments in those first four hours. 

“This is the most critical initial compromise, with over 155 million weekly downloads on the root packages,” Wiz Research said in an email. 

Some of the compromised packages, including keyv, flat-cache and file-entry-cache, are present in more than 46% of all cloud environments, according to Wiz. “By comparison, back in the Shai-Hulud 2.0 campaign the most prevalent packages were only in about 28% of environments,” the company said. 

“Time will tell whether the eventual cost and impact outpaces past attacks, or whether adoption of hardening mechanisms such as package aging, and the usage of the relatively less aggressive Mini Shai-Hulud code as basis, will defray the final toll here,” Wiz Research added. 

Researchers from multiple firms sprung into action to monitor the widening attack spree and published indicators of compromise to help potential victims hunt for malicious activity in their systems. 

The Mini Shai-Hulud variant used in these attacks scoops up a trove of sensitive data, including npm, GitHub, AWS and continuous integration credentials. It also steals AI-related configuration files and cryptocurrency wallets, researchers said. 

Microsoft, Aikido, Socket and Wiz all said the same payload and pattern was observed across all affected packages, indicating a single attacker or threat cluster was behind the supply-chain attack and using multiple stolen tokens. 

The malware showcased a few pieces of new functionality, but retained the same core mechanisms that are hallmarks of Mini Shai-Hulud. 

“The evolution is consistent with what we’ve seen from them in past waves, however we don’t yet have the hard links” to confidently attribute the attacks to TeamPCP, Wiz Research said.

The notorious threat actor, which Google previously told CyberScoop it attributes to one core operator that was located in South Africa during at least some of the attacks, compromised and injected malicious code into more than 1,000 software packages in less than four months earlier this year.

The post Massive supply-chain attack compromises 440 packages under four hours appeared first on CyberScoop.

Malware targeting AI coding assistants and software developers’ automated workflows is spreading into more environments with more capabilities, placing defenders at a growing disadvantage.

A malware strain dubbed Sandworm_Mode, first discovered by Socket in February, represents a growing threat to software development. According to a CrowdStrike report, the self-propagating worm can spread through code repositories with minimal detection, raising alarms about software supply chains.

The malware’s capabilities are extensive, but not especially unique compared to the series of supply-chain worms known as Shai-Hulud, and more recently Mini Shai-Hulud.

“This is the new trend,” Adam Meyers, senior vice president of counter adversary operations at CrowdStrike, told CyberScoop. “This is something we’re seeing more and more. It’s the new hotness right now.”

Sandworm_Mode targets and steals sensitive data, including credentials, keys and secrets that unlock paths to additional services and dependencies throughout the AI toolchain. This includes AI assistants, cloud providers, API keys for nine major LLM providers, CI/CD pipelines and automated systems that build, test and publish code.

These actions blend in with tens of thousands of other commands occurring daily in any given environment infused with AI development tools. 

“Trying to find the signal of something malicious happening is very difficult because there’s so much noise out there,” Meyers said. 

The worm also paces itself, setting multi-day delays to separate initial access from follow-on malicious activity — creating a gap in victims’ telemetry windows, which makes it even more challenging for defenders to detect and attribute the chain of infection properly. 

“AI agents are pulling down all of these different dependencies continuously throughout the day,” Meyers said. “When you’re looking downrange from the perspective of the security operations team, you’re just seeing everybody pulling down these dependencies, and these dependencies self-unpacking and executing, so it just gets really, really noisy to try to find something bad happening.”

The malware covers its tracks further with a bit of a mean streak, by automatically destroying compromised environments if it can’t spread or accomplish its objectives.

“It’s well thought-through, and well developed, so somebody spent some time caring and feeding this thing,” Meyer said.

Despite CrowdStrike’s four-month review of Sandworm_Mode, the cybersecurity firm has yet to gain a firm handle on its intent, but Meyers said it is designed to attain a strong foothold, which could enable long-term access.

CrowdStrike hasn’t determined who is responsible for the malware, yet Meyers said he doesn’t think TeamPCP, a threat group that’s been on a rampage through open-source software this year, is involved. 

“It could be a nation-state threat actor, or it could be an e-crime actor that’s looking to use this to then sell access to other organizations,” he said. “We don’t really know what the intention is.”

The state of Sandworm_Mode and whether it remains active is also unclear. CrowdStrike said it continues to observe recently active malicious supply-chain packages that follow similar but technically divergent patterns.

Ultimately, “the world has changed,” Meyers said, adding that many attackers are pursuing similar paths in the AI toolchain, requiring defenders and threat hunters to place a greater focus on this burgeoning mode of aggression.

The post Malware is targeting AI tools in software development environments appeared first on CyberScoop.