Technoholic.me
A new vulnerability in OpenAI ChatGPT lets malicious prompts secretly exfiltrate user data, including messages and files, without consent, warns Check Point. https://thehackernews.com/2026/03/openai-patches-chatgpt-data.html
OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerability

ChatGPT and Codex flaws patched Feb 2026 exposed DNS exfiltration and GitHub tokens, raising enterprise AI security risks.

The Hacker News
Apr 1 at 7:28pmradaar