Meta’s Muse AI Image Tool Uses Public Instagram Photos by Default
Meta has launched Muse Image, a new AI model that allows users to generate AI content using public Instagram posts and reels,…
Tag: CVE-2026-55200
Friendly Fire Attack: AI Coding Agents Tricked Into Running Malicious Code
Researchers at the AI Now Institute have published a proof-of-concept attack called 'Friendly Fire' that exploits AI coding agents designed to catch…
Fake 7-Zip Installers Recruit Devices into Lurking Lizard Proxy Botnet
Cybersecurity researchers at Infoblox have uncovered a threat actor tracked as Lurking Lizard, operating an end-to-end malicious residential proxy business since at…
GhostApproval Symlink Flaws Let Malicious Repos Execute Code in AI Coding Assistants
Security researchers at Wiz have identified a critical vulnerability pattern, dubbed GhostApproval, affecting six popular AI coding assistants. The flaw allows a…
AI Coding Agents Trigger Endpoint Security Rules Designed for Human Attackers
Sophos has identified that AI coding agents such as Claude Code, Cursor, and OpenAI Codex are triggering endpoint security rules originally designed…
Ubiquiti Patches Critical UniFi Flaws Across Connect, Talk, Access, Protect, and OS
Ubiquiti has released security updates to address multiple critical vulnerabilities across its UniFi product line, including UniFi Connect, UniFi Talk, UniFi Access,…
HalluSquatting Attack Exploits AI Coding Assistants to Deliver Botnet Malware
Researchers from Tel Aviv University, Technion, and Intuit have identified a novel attack vector called HalluSquatting that exploits AI coding assistants' tendency…
SCMBANKER Malware Uses ClickFix Lures to Target Mexican Banking Users
A new banking fraud operation tracked as REF6045 by Elastic Security Labs is targeting customers of Mexican banks, fintech platforms, payment processors,…
New Ghost Phishing Wave Using EvilTokens Bypasses Traditional Email Security
A recent EvilTokens campaign is exploiting a new 'ghost phishing' technique that hides malicious content until it decrypts inside the victim's browser,…
GitHub Copilot Refuses Harmful Requests in Chat, Then Writes Them in Code
Researchers Abhishek Kumar and Carsten Maple have discovered a novel workflow-level jailbreak method that bypasses safety guardrails in GitHub Copilot. The study,…