OpenAI patches ChatGPT flaw that smuggled data over DNS
ID: bad37bac-4944-5849-ad13-6c887d7dc3b0
STIX ID: report--bad37bac-4944-5849-ad13-6c887d7dc3b0
Feed Name: The Register (Security)
Threat Score
### Executive summary Check Point researchers found a DNS-based side-channel in ChatGPT's code execution/data analysis environment that allowed a single malicious prompt to exfiltrate uploaded user data to an attacker-controlled server; proof-of-concept attacks showed sensitive information leakage and OpenAI patched the issue on 2026-02-20.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.