Researchers found a botnet that targets unauthenticated Docker services, installs a language-model–driven agent, and uses Telegram and a model gateway to receive operator tasks and exfiltrate secrets.
CARBONATO exploits Docker daemons exposed without authentication to run privileged containers that gain host access and persistent footholds.
The attackers install an unmodified open-source Hermes Agent, replacing only its persona instructions so it collects secrets and follows Telegram-delivered commands processed through an LLM gateway.
It places an AI agent inside compromised systems, letting operators send tasks through Telegram and receive results. The campaign begins with Docker services carelessly exposed to the internet without authentication. Once inside, CARBONATO launches a privileged container, gains access to the host, establishes reboot persistence, and searches nearby networks for vulnerable servers.
This distinction matters because blocking every installation of a legitimate agent would also disrupt ordinary users. CARBONATO creates persistence through cron jobs, systemd timers, startup scripts, and OpenRC, then makes related files difficult to change. Its exposed image layers and configurations gave researchers a detailed view of the operation, underscoring the wider security risks of private container image exposure when registries lack proper access controls.
An operator's task travels with those instructions to the group's language model gateway. The model interprets the request, writes terminal commands, checks their output, and decides what to try next. The agent runs those commands on the victim server and reports back through Telegram.
Cybersecurity researchers have identified a threat actor that leverages artificial intelligence throughout the attack lifecycle to conduct search engine optimization (SEO) fraud, steal data, and maintain persistence in compromised environments. What is the threat? The threat actor, UAT-10147, uses a […]
Cisco Talos researchers created a new framework for identifying malware and hacking tools that rely on AI chatbots—and quickly discovered something unusual.
An internet-exposed cybercrime server linked to the BlackHatSect0r and DXQRTXX personas, revealing an operational environment that allegedly combined AI-assisted automation. Custom command-and-control tooling, phishing resources, stolen credentials, target lists, and internal operator communications. The exposure is no
Qrator found a Windows botnet advertised with AI API draining, credential theft and SOCKS5 proxying
A Russian-speaking threat actor has weaponized artificial intelligence at an unprecedented scale, deploying hundreds of autonomous AI agents to exploit critical vulnerabilities in PaperCut NG/MF print management software and compromise at least 440 servers across 395 organizations in 48 countries. Security researchers
Hackers have turned commercial AI models into working parts of a cyberattack operation. The campaign paired AI-directed tasking with familiar methods such as vulnerable public-facing servers, stolen credentials, webshells, and custom remote-access malware. The operation reached Taiwan’s Kuomintang Party History Archive
Loading more related stories...
Open the app view to save this story, compare related coverage, and continue from the same source.