OpenAI patches ChatGPT data exfiltration flaw and Codex GitHub token vulnerability
OpenAI has reportedly fixed a flaw that allowed data exfiltration from ChatGPT and a GitHub token vulnerability affecting Codex. The news was published on 30 March 2026.
Who is affected and how
- security leader
- Data leakage through AI tools poses a risk.
- developer
- Handling of access tokens in AI coding tools is an attack surface.
- journalist and researcher
- The patched flaws are examples of attacks on AI systems.
Sources
- OpenAI Patches ChatGPT Data Exfiltration Flaw and Codex GitHub Token Vulnerabilitythe hacker news · Mar 30, 2026
- OpenAI Codex vulnerability enabled GitHub token theft via command injection, report finds - SiliconANGLEsiliconangle.com · Mar 30, 2026
- Critical Vulnerability in OpenAI Codex Allowed GitHub Token Compromise - SecurityWeeksecurityweek.com · Mar 31, 2026
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article. News monitoring and analysis, not security advice. Attributions belong to those who made them.
What do you make of this piece?
The split shows after 20 votes.
Why? Your answer is not shown publicly; it helps the editors.