Google’s Gemini is the latest AI model to hack other companies


Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks.

Similar to OpenAI’s breach of Hugging Face, the Gemini hacks were less noteworthy for being particularly sophisticated and more for the fact that they were conducted by an AI model. These breaches took place during cybersecurity testing by a company called Irregular. In one case, Gemini simply guessed passwords until it gained access; in the other two, it found credentials in a public repository.

Read more…
Source:  TechCrunch News


Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox


Related:

  • Microsoft fixes record 964 flaws, including 2 exploited zero-days

    September 9, 2026

    Microsoft’s September 2026 Patch Tuesday addresses 964 CVEs, including 104 rated Critical and 860 rated Important, making it the company’s largest Patch Tuesday release on record. Microsoft lists 974 CVEs in its full September security release. However, 10 of those affect cloud services or involve fixes that Microsoft applies itself, leaving 964 vulnerabilities that customers need to patch. The ...

  • MikroTik router flaws allow takeover without a password

    September 8, 2026

    CERT Polska warns that attackers are actively exploiting a chain of critical MikroTik RouterOS flaws to seize control of routers exposed to the internet. Although the warning comes from Poland’s national cybersecurity response team, MikroTik routers are sold worldwide, including in the US. The vulnerabilities can affect users anywhere if their router is running a vulnerable version ...

  • Two major security flaws are affecting more than six million WordPress websites

    September 7, 2026

    More than six million WordPress users are at risk of website takeover, researchers have claimed after discovering two major vulnerabilities being exploited in the wild. Security researchers Wordfence disclosed finding two flaws, one in Elementor Pro, and one in Super Forms – two popular WordPress plugins. Elementor Pro is a commercial plugin that allows users to build websites using ...

  • More than 1 million users affected in Mathspace data breach across Australia and New Zealand

    September 7, 2026

    More than a million people, including students, school staff, and parents, have been affected following a data breach at Mathspace, according to the learning provider. The company said, in a blog post, “unauthorised parties had accessed an internal reporting system used by Mathspace” and the exposed information included names and email addresses. It said the attackers accessed ...

  • G7 tells businesses to get ready for quantum cybersecurity threats

    September 7, 2026

    The G7, a collection of some of the world’s most powerful economies, is urging organizations to adopt quantum-resistant encryption as soon as possible and minimize the risk of losing sensitive data to technologically advanced threat actors. Virtually every industry in the world today relies on encryption (the process of converting readable data into scrambled, unreadable data ...

  • Dissecting a PHP web server rootkit

    September 7, 2026

    SophosLabs recently acquired a Linux implant associated with compromised BIG-IP Access Policy Management (APM) environments that use Apache and PHP components. The malware demonstrates advanced techniques including custom ELF loading, function hooking, and runtime code patching to evade detection while maintaining persistent access through hidden web shells. The implant delivers a familiar outcome – on-demand server‑side ...