Gemini is a tool tracked across 50 threat clusters and 112 intelligence report mentions on ThreatCluster. First observed November 5, 2025; most recent activity July 17, 2026.
A Cambridge University study reveals Boko Haram has integrated AI tools into its operations, utilizing US and Chinese chatbots for bomb-making, attack planning, and propaganda. The research, based on interviews with 27…
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…
Recent reports indicate that state-linked hackers are leveraging artificial intelligence to enhance their cyber capabilities, posing significant risks to national utilities and intellectual property. Additionally, a US…
Google has filed a lawsuit against the 'Outsider Enterprise', a China-based cybercrime network, for allegedly using AI tools, including its Gemini platform, to conduct large-scale phishing operations. The operation has…
In July 2026, researchers demonstrated that open-weight AI models can be easily poisoned, allowing attackers to implant backdoors for under $100. Katie Paxton-Fear successfully manipulated a model to execute remote code…
The Infocomm Media Development Authority (IMDA) of Singapore issued an advisory on May 14, 2026, cautioning against the use of OpenClaw in mission-critical environments. OpenClaw, an AI tool released in November 2025 by…
A new supply chain attack, dubbed 'Mini Shai-Hulud', has compromised multiple npm packages related to SAP's Cloud Application Programming Model (CAP). This attack involves injecting malicious preinstall scripts into…
Two Chrome extensions, 'Smart Adblocker' and 'Adblock for Browser', have been discovered to exfiltrate user prompts and responses from major AI platforms including ChatGPT, Claude, and Gemini. These extensions,…
On May 20, 2026, GitHub confirmed a significant security breach involving a poisoned Visual Studio Code (VS Code) extension that compromised an employee's device. The attack, attributed to the TeamPCP hacking group,…
Researchers at the University of Toronto have developed a self-replicating AI worm that autonomously exploits network vulnerabilities. This malware utilizes a small, free large language model (LLM) to devise unique…