Google Gemini is a technology platform tracked across 20 threat clusters and 33 intelligence report mentions on ThreatCluster. First observed November 10, 2025; most recent activity July 4, 2026.
The GREYVIBE group, a previously unknown Russian hacking entity, has been actively targeting Ukrainian military, government, and civilian sectors since August 2025. Utilizing sophisticated AI tools like ChatGPT and…
A Cisco study has found that 15 major AI models from OpenAI, Anthropic, Google, Amazon, and xAI are significantly more vulnerable to multi-turn prompt injection attacks than previously reported. The research tested…
A study by Wake Forest University revealed that 282 out of 444 analyzed iOS applications with AI features are leaking Large Language Model (LLM) API credentials through network traffic. This vulnerability affects apps…
A Russian-speaking hacker, identified as bandcampro, utilized a jailbroken Google Gemini to execute a cybercrime campaign targeting MAGA supporters from September 2025 to May 2026. The operation involved impersonating…
Michael Bargury, CTO of Zenity, revealed that enterprise AI agents are highly susceptible to zero-click attacks, which exploit their gullibility. These attacks can manipulate AI systems like Cursor, Salesforce, and…
Delhi Police have arrested multiple individuals involved in cyber fraud schemes, including a stock market scam that defrauded victims of Rs 14 lakh and APK-based frauds totaling Rs 80,825. The stock market scam involved…
For the first time in history, automated bots have overtaken human users in global internet traffic, with bots generating 57.5% of all HTTP requests. This shift, confirmed by Cloudflare data, occurred significantly…
A newly discovered vulnerability in Google Gemini's voice assistant allows attackers to exploit indirect prompt injection through notifications from popular messaging apps like WhatsApp and Slack. Researchers at…
ESET researchers have identified PromptSpy, the first Android malware to incorporate generative AI, specifically Google’s Gemini, in its execution flow. This malware utilizes AI to manipulate the user interface and…
Researchers have identified multiple vulnerabilities in OpenAI's ChatGPT, including seven critical flaws that allow attackers to exfiltrate personal data, inject malicious prompts, and manipulate the AI's memory. The…