7 articles tagged with "Chatgpt"
Researchers discover ChatGPT's Markdown rendering trusts attacker-controlled content from summarized pages, enabling phishing URLs, IP exfiltration, and fake security alerts inside the AI interface.
Check Point Research disclosed a ChatGPT vulnerability that abused DNS tunneling to silently steal conversation data. OpenAI patched the flaw on February 20, 2026.
LayerX researchers found that custom font rendering can hide malicious prompts from ChatGPT, Claude, Gemini, and other AI assistants while displaying them to users.
Three ClickFix campaigns target macOS users with MacSync infostealer disguised as ChatGPT and AI coding tools. Latest variant adds in-memory execution to evade detection.
AI company will begin testing advertisements in ChatGPT for US users in coming weeks, projecting $1 billion in ad revenue by end of 2026.
Two rogue browser extensions masquerading as AI tools exfiltrated complete conversation histories from ChatGPT and DeepSeek to attacker-controlled servers every 30 minutes.
Urban VPN and related browser extensions secretly harvest conversations from ChatGPT, Claude, Copilot, and other AI platforms, selling data to advertisers.