SafeBreach Demonstrates Prompt Injection Attack on Gemini
SafeBreach, a cybersecurity company, demonstrated an indirect prompt injection attack that could hijack Gemini's Android Utilities agent via notification content, which Google…
Tag: Gemini
OpenClaw AI Agent Vulnerable to Code Execution and Data Exfiltration via Hidden Commands and Phishing
Two security teams have demonstrated that OpenClaw, a popular self-hosted AI agent, can be tricked into executing attacker-controlled code or leaking sensitive…
Google Sues Chinese Smishing Network Using Gemini AI for Phishing
Google has filed a lawsuit against a Chinese cybercrime network accused of using its Gemini AI agent to power a phishing-as-a-service (PhaaS)…
Outsider Enterprise: Chinese Phishing-as-a-Service Network
A Chinese cybercrime network operating the Outsider PhaaS platform, using Gemini AI for phishing. Coordinated via Telegram, it includes Developer, Data Broker,…
Outsider Phishing-as-a-Service Kit
A PhaaS kit offering pre-built templates, keystroke logging, and AI integration. Used to create fraudulent websites and launch smishing campaigns.
Malicious JetBrains Plugins Steal AI API Keys; Chrome Extensions Capture Chatbot Chats
Cybersecurity researchers have uncovered a coordinated malware campaign on the JetBrains Marketplace involving 15 malicious plugins that exfiltrate AI provider API keys.…
Gemini Deep Thinking Mode Vulnerable to Cryptographic Payload Injection
Google's Gemini in Deep Thinking mode was shown to be vulnerable to a similar attack, producing restricted content and reproducing system instructions.…