Find notable cyber news and cases, enriched with sources, timelines, and signals.
Home Browse News Feed Stats Watchlists Beta About Contact

ChatGPT Atlas persistent memory CSRF memory corruption flaw

Vulnerability
First reported
Last updated
Happening score
H score 0
1 unique sources, 1 articles

Summary

Hide ▲

ChatGPT Atlas has a CSRF flaw that can inject malicious instructions into persistent memory, creating a pathway to arbitrary code execution across sessions and devices. The flaw can also enable account takeover, privilege escalation, and data exfiltration when a logged-in user later uses ChatGPT normally. The issue matters because the tainted memory can survive until it is explicitly deleted.

Related Happenings

Tenable's ChatGPT prompt-injection and url_safe bypass analysis

Technical Analysis
First: 06.11.2025 17:49 Last: 06.11.2025 17:49 Sources 1

About this happening: Tenable uncovered **seven ChatGPT vulnerabilities** that let attackers drive **prompt injection**, **phishing redirects**, and **memories/chat history exfiltration** through **Sea...

Open Happening

ChatGPT/SearchGPT prompt injection and data exfiltration weaknesses security flaw

Vulnerability
First: 06.11.2025 12:00 Last: 06.11.2025 12:00 Sources 1

About this happening: Researchers uncovered **seven weaknesses** in **OpenAI's ChatGPT/SearchGPT** that could let an attacker use **prompt injection** and **safety bypass** techniques to steal **privat...

Open Happening

OpenAI ChatGPT indirect prompt injection vulnerabilities GPT-4o/GPT-5 security flaw

Vulnerability
First: 05.11.2025 16:04 Last: 05.11.2025 16:04 Sources 1

About this happening: **OpenAI's ChatGPT** has a newly disclosed set of **indirect prompt injection** flaws in **GPT-4o and GPT-5** that could let an attacker steal data from **users' memories and chat...

Open Happening

Timeline

  1. 27.10.2025 16:31 1 articles · 7mo ago

    ChatGPT Atlas CSRF flaw exposes persistent memory to hidden instruction injection

    Initial Disclosure

    LayerX Security identifies a new vulnerability in OpenAI's ChatGPT Atlas web browser that uses a cross-site request forgery (CSRF) flaw to inject malicious instructions into ChatGPT's persistent memory. The tainted memory can persist across devices and sessions and may later trigger arbitrary code execution, privilege escalation, account takeover, browser compromise, or data exfiltration when a logged-in user makes normal ChatGPT requests.

    Show sources
    Open in new tab