threat-intel New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands Researchers at Seoul National University, the University of Illinois Urbana-Champaign, and Largosoft have discovered a new attack method called Agent Data Injection (ADI) that can manipulate AI agents by subtly corrupting the trusted data they rely on. Instead of directly injecting commands, attackers plant fake inform… The Hacker News · Jul 16, 2026 High CVE-2025-32711prompt-injectiondata-exfiltrationai-security
threat-intel New MemGhost Attack Plants Persistent False Memories in AI Agents Through One Email Researchers have developed MemGhost, an automated tool that can plant false memories in AI assistants by sending a single, carefully crafted email. The tool bypasses existing security measures by exploiting the agents' a… The Hacker News · Jul 13, 2026 High CVE-2025-32711aimemory poisoningemail
threat-intel One-Click Microsoft 365 Copilot Flaw Could Have Let Attackers Steal Emails, Files, and MFA Codes A vulnerability, dubbed SearchLeak, was discovered in Microsoft 365 Copilot Enterprise Search that allowed attackers to exfiltrate sensitive data like emails, calendar details, and MFA codes through a single click. The f… The Hacker News · Jun 15, 2026 High CVE-2026-42824CVE-2025-32711UScommand injectionprompt injectionbing
