Latest cybersecurity reporting from selected sources.

TrendAI™ Research analyzed over 200 Gemini CLI session logs showing how a Russian-speaking threat actor used AI to run a live botnet, finishing a full C&C migration in six minutes while doing just 11% of the work himself.

Cybersecurity researchers have disclosed details of a now-patched critical session isolation vulnerability in Writer, an enterprise generative artificial intelligence (AI) platform, that could result in cross-tenant compromise

AI Dependency Attack Reportedly Exposes Data and Source CodeA LiteLLM supply-chain compromise enabled attackers to harvest credentials and access internal environments at scale at Mercor. The firm was the first to confirm a LiteLLM breach, and researchers are warning about growing AI system exposure and limited visibility.

Cybersecurity researchers have disclosed a security "blind spot" in Google Cloud's Vertex AI platform that could allow artificial intelligence (AI) agents to be weaponized by an attacker to gain unauthorized access to sensitive data and compromise an organization's cloud environment

Huntress researchers said it’s likely the victims they've identified represent just a fraction of compromised organizations worldwide. The post An AI-powered phishing campaign has compromised hundreds of organizations appeared first on CyberScoop.

Cybersecurity researchers have discovered a malicious npm package that masquerades as an OpenClaw installer to deploy a remote access trojan (RAT) and steal sensitive data from compromised hosts

Cybersecurity researchers have flagged a new malicious Microsoft Visual Studio Code (VS Code) extension for Moltbot (formerly Clawdbot) on the official Extension Marketplace that claims to be a free artificial intelligence (AI) coding assistant, but stealthily drops a malicious payload on compromised hosts

The North Korean threat group is using a new PowerShell backdoor to compromise development environments and target cryptocurrency holdings, according to researchers.

Cybersecurity researchers have disclosed details of a new attack method dubbed Reprompt that could allow bad actors to exfiltrate sensitive data from artificial intelligence (AI) chatbots like Microsoft Copilot in a single click, while bypassing enterprise security controls entirely

Cybersecurity researchers have disclosed details of a phishing campaign that delivers a stealthy banking malware-turned-remote access trojan called MostereRAT

'Widespread Data Theft Campaign' Compromised Many Drift OAuth Tokens, Warn ExpertsThreat researchers report that "a widespread data theft campaign" traces to attackers stealing OAuth access tokens for applications integrated with Salesloft's AI chatbot Drift, then exfiltrating data. Victims include Salesforce customer Zscaler. Google Workspace instances were also breached.

Wiz Research details flaws in Python backend that expose AI models and enable remote code execution Security researchers have lifted the lid on a chain of high-severity vulnerabilities that could lead to remote code execution (RCE) on Nvidia's Triton Inference Server.…

Cybersecurity researchers have called attention to a new campaign that's actively exploiting a recently disclosed critical security flaw in Langflow to deliver the Flodrix botnet malware

Cybersecurity researchers have discovered an updated version of a malware loader called Hijack Loader that implements new features to evade detection and establish persistence on compromised systems

Cybersecurity researchers have discovered several cryptocurrency packages on the npm registry that have been hijacked to siphon sensitive information such as environment variables from compromised systems

Cybersecurity researchers have disclosed details of a new supply chain attack vector dubbed Rules File Backdoor that affects artificial intelligence (AI)-powered code editors like GitHub Copilot and Cursor, causing them to inject malicious code

Kela researchers explain that infostealers are to blame for compromised OpenAI logins

Amateurish Ransomware Group Doubles as HackstivistsCybersecurity researchers discovered an artificial intelligence-driven ransomware group that emerged at the end of last year and compromised more than 85 victims worldwide. The group uses double extortion, combining data theft with encryption.

Bad actors have been observed targeting Docker remote API servers to deploy the SRBMiner crypto miner on compromised instances, according to new findings from Trend Micro

Attack Method Exploits RAG-based Tech to Manipulate AI System's OutputResearchers found an easy way to manipulate the responses of an artificial intelligence system that makes up the backend of tools such as Microsoft 365 Copilot, potentially compromising confidential information and exacerbating misinformation. Researchers called the attack "ConfusedPilot."