AI · 168 days ago

ChatGPT side‑channel could leak conversations; OpenAI patched

Check Point found a ChatGPT flaw that let a crafted prompt make the model exfiltrate conversation text and uploaded files through a DNS-based side channel in the Linux code-execution runtime. OpenAI released fixes for ChatGPT and a separate Codex GitHub token issue on February 20, 2026. Researchers say there is no evidence the flaw was exploited in the wild.

Timeline

• Mar 31 Reported by SecurityWeek
• Mar 31 Reported by The Hacker News

Sources

2 sources covering this story

• SecurityWeek Mar 31

  Critical Vulnerability in OpenAI Codex Allowed GitHub Token Compromise

  Researchers found an OpenAI Codex vulnerability that could have been exploited to compromise GitHub tokens.

• The Hacker News Mar 31

  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.

Part of the PlainSec briefing for 2026-03-31

Editions

• Briefing for 2026-03-31