Signal

OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerability

Evidence first: scan the strongest sources, then decide whether to go deeper.

Published 2026-03-30 18:05 UTCUpdated 2026-03-31 13:01 UTC
rss
securitychatgpt_security_issue
Source links open
Source links and full evidence are open here. Archive history, compare-over-time, alerts, exports, API, integrations, and workflow are paid.
No card needed for the free brief.
Evidence trail (top sources)
top sources (3 domains)domains are deduped. counts indicate coverage, not truth.
3 top sources shown
ChatGPT Security Issue Enabled Data Theft via Single Prompt
Infosecurity Magazine · News · infosecurity-magazine.com · 2026-03-31 13:01 UTC
Overview

OpenAI has patched vulnerability, which Check Point said was because of a DNS loophole.

Score total
1.26
Momentum 24h
3
Posts
3
Origins
3
Source types
1
Duplicate ratio
0%
All evidence
All evidence
ChatGPT Security Issue Enabled Data Theft via Single Prompt
Infosecurity Magazine · infosecurity-magazine.com · 2026-03-31 13:01 UTC
Critical Vulnerability in OpenAI Codex Allowed GitHub Token Compromise
SecurityWeek · securityweek.com · 2026-03-31 06:35 UTC
OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerability
The Hacker News · thehackernews.com · 2026-03-30 18:05 UTC
Show filters & breakdown
Posts loaded: 0Publishers: 3Origin domains: 3Duplicates: -
Showing 3 / 0
Top publishers (this list)
  • Infosecurity Magazine (1)
  • SecurityWeek (1)
  • The Hacker News (1)
Top origin domains (this list)
  • infosecurity-magazine.com (1)
  • securityweek.com (1)
  • thehackernews.com (1)