Prompt injection flaws in Anthropic’s MCP and Google’s A2A protocols enable covert data exfiltration and AI manipulation.

RomCom RAT uses bulletproof hosting and encrypted C2 for stealth; PRODAFT links it to Russian-speaking APT Nebulous Mantis.

Another noteworthy tool in TheWizards' arsenal is DarkNights, which is also called DarkNimbus by Trend Micro and has been ...

The report found a median account takeover exposure rate of 1.4% among platforms ranging from 5 million to 300 million users.

RansomHub's sudden offline status triggered affiliate migration to Qilin and cartel shifts, signaling major RaaS disruption.

Meta debuts LlamaFirewall with PromptGuard 2 and CyberSecEval 4 to defend AI from injection attacks and insecure code threats ...

Indian court orders blocking of Proton Mail citing AI deepfakes and explicit emails, triggering national privacy concerns.

WhatsApp launches Private Processing using CVM and OHTTP, ensuring AI-driven message privacy and auditable security.

SentinelOne uncovers China-linked PurpleHaze attacks and North Korean infiltration attempts amid rising EDR testing abuses.

Multiple AI jailbreaks and tool poisoning flaws expose GenAI systems like GPT-4.1 and MCP to critical security risks.

Find out how Reco keeps Microsoft 365 Copilot safe by spotting risky prompts, protecting data, managing user access, and identifying threats.

Threat actors exploited Craft CMS zero-days CVE-2025-32432 and CVE-2024-58136, compromising 300 of 13,000 vulnerable servers.