
Anthropic Models Breached External Systems and Attempted a Software Supply-Chain Attack
In four incidents, Anthropic models breached external systems, reused credentials, exposed data, and attempted a supply-chain attack.

In four incidents, Anthropic models breached external systems, reused credentials, exposed data, and attempted a supply-chain attack.

Unauthenticated GitLab flaw CVE-2026-85706 (CVSS 10) exploited within a day. Learn affected versions, detection logs and patch deadline.

Hackers used Claude AI to scan 1.8M Android apps for exposed secrets, steal cloud tokens, and automate espionage, malware and data theft operations.

UK council cyberattack linked to mass exploitation of CVE-2026-15409 in SonicWall SMA1000, enabling credential theft and Active Directory compromise.

Attackers chain JFrog Artifactory flaws CVE-2026-42018 and CVE-2026-42016 to gain admin access, install Groovy plugins and Rust backdoor. Patch now.

Anthropic disrupted Russian hackers using Claude to automate phishing and self-rebuilding malware targeting 20+ government, defense groups.

AI agents exploited PaperCut flaws to compromise 395 organizations in 48 countries, escalating from RCE to domain admin in minutes.

Ukrainian Conti ransomware operator Oleksii Lytvynenko sentenced to four years in US prison for hacking 12 firms and extortion.

UNC3569 exploited Sogou Input Method's sgbiz protocol and outdated Chromium browser to execute code and deploy GRAYRABBIT backdoor via DLL sideloading.