Back Cybersecuritynews

Google Warns of Hackers Leveraging Gemini AI Model for All Stages of Cyberattacks

Cybersecuritynews •Guru Baran • February 12, 2026

Threat actors have begun leveraging Google’s Gemini API to dynamically generate C# code for multi-stage malware, evading traditional detection methods. The Google Threat Intelligence Group (GTIG) detailed this in its February 2026 AI Threat Tracker report, spotlighting the HONESTCUE framework first observed in September 2025. HONESTCUE operates as a downloader and launcher that queries Gemini’s […]

The full story

This article is one source in a clustered incident — the cluster page carries the summary, timeline and every other outlet covering it.

State-Sponsored Hackers Exploit Google's Gemini AI for Cyberattacks State-backed hackers from China, Iran, North Korea, and Russia are utilizing Google's Gemini AI model to facilitate various stages of cyberattacks, including reconnaissance and post-compromise actions. Notably, the Chinese group APT31 has employed Gemini to analyze vulnerabilities and plan attacks against U.S. organizations, although no successful breaches have been reported. 140 sources 33

Extracted Entities

Google Warns of Hackers Leveraging Gemini AI Model for All Stages of Cyberattacks

The full story

Extracted Entities

Attack Types (1)

Malware (1)

MITRE ATT&CK (1)

Tools (2)