ChatGPT and Codex flaws patched Feb 2026 exposed DNS exfiltration and GitHub tokens, raising enterprise AI security risks.
5don MSN
Security experts discover critical flaw in OpenAI's Codex able to compromise entire organizations
Researchers managed to steal GitHub OAuth tokens by abusing a command injection vulnerability.
What happens when researchers think outside the box? Data gets exfiltrated through DNS.
Command injection in Codex and a hidden outbound channel in ChatGPT exposed risks of credential theft and covert data ...
Security researchers at BeyondTrust Phantom Labs discovered a critical flaw in OpenAI's Codex coding agent that allowed an ...
OpenAI patches ChatGPT vulnerability that allowed silent data exfiltration and fixes Codex flaw exposing GitHub tokens.
ChatGPT is bringing its Deep Research service directly into GitHub's developer ecosystem. This integration is beginning a beta test this week, with ChatGPT Plus, Pro and Team users the first to ...
Following the GitHub connector for source code research, ChatGPT can now integrate with Microsoft OneDrive and SharePoint for deep research on documents. Last week, OpenAI announced a GitHub connector ...
ChatGPT has 200+ apps and agentic commerce is live, growing fast, and most brands are invisible in it. Here is what DaVinci ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results