Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-7021— OpenAI Operator - API Spoofing through Locking Operator on FullScreen

Quick assessment

Affected
OpenAI Operator
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

OpenAI Operator是美国OpenAI个人开发者的一个人工智能代理。 OpenAI Operator存在安全漏洞，该漏洞源于全屏API和UI渲染处理不当，可能导致远程攻击者通过欺骗性全屏界面捕获敏感用户输入。

AI Predicted 6.1 Difficulty: Easy EPSS 0.36% · P28
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-7021

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
OpenAI Operator - API Spoofing through Locking Operator on FullScreen
Source: CVE Program / CVE List V5
Vulnerability Description
Fullscreen API Spoofing and UI Redressing in the handling of Fullscreen API and UI rendering in OpenAI Operator SaaS on Web allows a remote attacker to capture sensitive user input (e.g., login credentials, email addresses) via displaying a deceptive fullscreen interface with overlaid fake browser controls and a distracting element (like a cookie consent screen) to obscure fullscreen notifications, tricking the user into interacting with the malicious site.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:N/VA:N/SC:H/SI:N/SA:N
Source: CVE Program / CVE List V5
Vulnerability Type
关键信息的UI错误表达
Source: CVE Program / CVE List V5
Vulnerability Title
OpenAI Operator 安全漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
OpenAI Operator是美国OpenAI个人开发者的一个人工智能代理。 OpenAI Operator存在安全漏洞，该漏洞源于全屏API和UI渲染处理不当，可能导致远程攻击者通过欺骗性全屏界面捕获敏感用户输入。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
OpenAI Operator SaaS -

II. Public POCs for CVE-2025-7021

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2025-7021

请登录查看更多情报信息。

IV. Related Vulnerabilities

Same product: Operator
Same vendor: OpenAI
Same weakness: CWE-451

V. Comments for CVE-2025-7021

No comments yet

Leave a comment