Threats Tagged 'amos stealer'

Threat actors are actively exploiting AI distribution platforms like Hugging Face and ClawHub to deliver malware by embedding malicious code within models, datasets, and agent extensions. Over 575 malicious skills across 13 developer accounts were identified in the OpenClaw ecosystem, targeting Windows and macOS with trojans, cryptominers, and AMOS stealer. Attackers abuse trust relationships between users and AI platforms through indirect prompt injection, where hidden instructions cause AI agents to execute malicious actions on behalf of users. Trojanized skills masquerade as legitimate tools while instructing users to execute encoded commands or install hidden malicious dependencies. On Hugging Face, repositories host payloads within multistep infection chains disguised as legitimate applications. These campaigns employ social engineering, obfuscation, encryption, in-memory execution, process injection, and persistence techniques to evade detection while establishing covert command-and-control communica...

On April 23, 2026, Field Effect MDR identified AMOS Stealer malware delivered through a novel technique exploiting Cursor AI agent sessions running Claude Code. The attack employed social engineering to manipulate operators into prompting the AI agent to download and execute malicious AppleScript loaders. The heavily obfuscated scripts performed sandbox evasion checks, collected sensitive data including credentials, SSH keys, browser data, and cryptocurrency wallets, then exfiltrated compressed archives to remote servers within two minutes. The malware prompted users for local account credentials through fake macOS system dialogs, subsequently using elevated permissions to install persistent implants masquerading as legitimate system services. This delivery mechanism makes detection challenging as malicious commands blend with typical agentic coding behavior, representing an evolution in AMOS Stealer tactics beyond traditional SEO poisoning methods.