Last seen October 31, 2025

ChatGPT Remote Code Execution Vulnerability

Evidence indicates that ChatGPT is affected by remote code execution.

Technical Severity

Low severity

Lifecycle Status

DEVELOPING

Sources

2 sources: thehackernews.com +1

What Happened

Evidence indicates that ChatGPT is affected by remote code execution.

Why This Matters

The evidence matters to defenders using ChatGPT because it could let an attacker run code in affected environments.

Recommended Action

No confirmed vendor remediation is available in the current evidence. Confirm whether ChatGPT is present in your environment and review the affected configuration.

Follow this incident as it develops Material-change notifications are being prepared for BugSkan Pro.

Exposure

Recommended Response

First Seen

Oct 27, 2025 05:30

Last Seen

Oct 31, 2025 05:30

Exploitation status: UNKNOWN

Primary entities:

OpenAI ChatGPT AI Agents Remote Code Execution

Timeline

Incident first seen
Oct 27, 2025 05:30
BugSkan first recorded this incident.
New ChatGPT Atlas Browser Exploit Lets Attackers Plant Persistent Hidden Commands - The Hacker News
Oct 27, 2025 05:30
thehackernews.com · Vulnerability
OpenAI Unveils Aardvark: GPT-5 Agent That Finds and Fixes Code Flaws Automatically - The Hacker News
Oct 31, 2025 05:30
thehackernews.com · Vulnerability
Latest observed development
Oct 31, 2025 05:30
Most recent source or update associated with this incident.
Material change
Aug 18, 2026 14:07
ACT -> WATCH
Material change
Aug 18, 2026 14:07
recommended action updated
Material change
Aug 18, 2026 14:07
why it matters updated
Material change
Aug 18, 2026 14:07
severity 7.5 -> 6.0

Sources

New ChatGPT Atlas Browser Exploit Lets Attackers Plant Persistent Hidden Commands - The Hacker News

thehackernews.com · Oct 27, 2025 05:30

A critical vulnerability in OpenAI's ChatGPT Atlas browser leverages a Cross-Site Request Forgery (CSRF) flaw to inject malicious instructions into the AI's persistent memory. This allows attackers to achieve arbitrary code execution and gain control over user accounts or systems across sessions, triggered by legitimate user interaction with the compromised AI.

Open publisher source

OpenAI Unveils Aardvark: GPT-5 Agent That Finds and Fixes Code Flaws Automatically - The Hacker News

thehackernews.com · Oct 31, 2025 05:30

OpenAI has launched Aardvark, an AI agent powered by GPT-5, engineered to autonomously scan, identify, validate, and propose patches for security vulnerabilities in source code. This agent integrates into the SDLC to provide continuous protection, and has successfully identified at least 10 CVEs in various open-source projects.

Open publisher source

Watchlist Match

Want personalized relevance?

Create an account to see which incidents overlap with the technologies you monitor.