First Known Android AI Malware Uses Google’s Gemini for Decision-making
The first known Android malware family to weaponize a generative AI model, specifically Google’s Gemini, as part of its active execution flow. Discovered in February…
The first known Android malware family to weaponize a generative AI model, specifically Google’s Gemini, as part of its active execution flow. Discovered in February…
A critical advisory warning regarding a severe vulnerability affecting Honeywell CCTV products, published on February 17, 2026, under advisory ICSA-26-048-04. The alert details a high-severity…
Microsoft Defender Centralized Script Library Microsoft has introduced a new Library Management experience in Microsoft Defender for Endpoint, designed to fundamentally transform how security analysts…
XWorm Malware Steals Logins via Receipts A sophisticated multi-stage malware campaign is actively targeting Brazilian and Latin American (LATAM) businesses using fake bank receipts to…
Threat actors have begun using an obfuscation technique called emoji smuggling to hide malicious code from security systems. This attack method exploits Unicode encoding and…
Authentication Bypass better-auth API Keys A critical authentication bypass vulnerability in the better-auth API keys plugin allows unauthenticated attackers to mint privileged API keys for…
A compromised publish token gave attackers brief but concerning access to the Cline CLI npm package, exposing developers who installed it during an 8-hour window…
A sophisticated cryptocurrency mining campaign has emerged, targeting systems through external storage devices with the ability to compromise even air-gapped environments. The malware operates as…
The Model Context Protocol (MCP) emerged as a breakthrough standard in November 2024, designed by Anthropic to seamlessly connect AI assistants with external systems and…
Microsoft is rolling out a significant update to Teams Mobile on Android and iOS that changes how non-Office and PDF links are handled within the…
OpenAI EVMbench OpenAI, in collaboration with crypto investment firm Paradigm, has introduced EVMbench, a new benchmark designed to evaluate the ability of AI agents to…
Guardian AI-Penetration Testing Tool A new open-source framework is reshaping how security professionals approach penetration testing by placing multiple large language models directly at the…