Securitybrief

Seven Vulnerabilities in ChatGPT Expose User Data to Attack

First seen 6 Nov 2025, 17:37 UTC • Tenable

•82% similarity •49.3

Ask AI about this cluster

Article Content

Include sub-articles 1 / 1

Browse articles

ThreatCluster

Tenable Research identified seven vulnerabilities in OpenAI's ChatGPT models that could allow attackers to steal personal data and manipulate conversations. These flaws, affecting ChatGPT-4o and ChatGPT-5, include methods for data exfiltration and bypassing safety mechanisms. Users are at risk of data leakage and persistent malicious instructions due to these security issues.

ThreatCluster AI

Attack Flow

20 entities, 53 inferred relationships (STIX 2.1).

Technique (3)

Data Breach
Phishing
Prompt Injection

Organization (2)

OpenAI
Tenable Research

Indicator (2)

bing.com
llmninjas.com

Affected Platform (4)

Bing
ChatGPT
ChatGPT-4o
ChatGPT-5

Tool (1)

SearchGPT

Vulnerability (8)

Data leakage vulnerabilities
HackedGPT
Indirect Prompt Injection
Jailbreaking techniques
memory injection
One-click vulnerability
Persistent Memory Injection
Zero-click vulnerability

Relationships

SearchGPT exploits Data leakage vulnerabilities
SearchGPT exploits HackedGPT
SearchGPT exploits Indirect Prompt Injection
SearchGPT exploits Jailbreaking techniques
SearchGPT exploits memory injection
Data leakage vulnerabilities targets Bing
Data leakage vulnerabilities targets ChatGPT
Data leakage vulnerabilities targets ChatGPT-4o
Data leakage vulnerabilities targets ChatGPT-5
HackedGPT targets Bing
HackedGPT targets ChatGPT
HackedGPT targets ChatGPT-4o
HackedGPT targets ChatGPT-5
Indirect Prompt Injection targets Bing
Indirect Prompt Injection targets ChatGPT
Indirect Prompt Injection targets ChatGPT-4o
Indirect Prompt Injection targets ChatGPT-5
Jailbreaking techniques targets Bing
Jailbreaking techniques targets ChatGPT
Jailbreaking techniques targets ChatGPT-4o
Jailbreaking techniques targets ChatGPT-5
memory injection targets Bing
memory injection targets ChatGPT
memory injection targets ChatGPT-4o
memory injection targets ChatGPT-5
One-click vulnerability targets Bing
One-click vulnerability targets ChatGPT
One-click vulnerability targets ChatGPT-4o
One-click vulnerability targets ChatGPT-5
Persistent Memory Injection targets Bing
Persistent Memory Injection targets ChatGPT
Persistent Memory Injection targets ChatGPT-4o
Persistent Memory Injection targets ChatGPT-5
Zero-click vulnerability targets Bing
Zero-click vulnerability targets ChatGPT
Zero-click vulnerability targets ChatGPT-4o
Zero-click vulnerability targets ChatGPT-5
Data Breach targets Bing
Data Breach targets ChatGPT
Data Breach targets ChatGPT-4o
Data Breach targets ChatGPT-5
Phishing targets Bing
Phishing targets ChatGPT
Phishing targets ChatGPT-4o
Phishing targets ChatGPT-5
Prompt Injection targets Bing
Prompt Injection targets ChatGPT
Prompt Injection targets ChatGPT-4o
Prompt Injection targets ChatGPT-5
Data leakage vulnerabilities related to OpenAI
Data leakage vulnerabilities related to Tenable Research
Data leakage vulnerabilities related to bing.com
Data leakage vulnerabilities related to llmninjas.com

Community

Browse all →

Tracked Entities in This Story

OpenAI Tenable Research Bing ChatGPT ChatGPT-4o ChatGPT-5 Data Breach Phishing Prompt Injection SearchGPT

Seven Vulnerabilities in ChatGPT Expose User Data to Attack

Ask AI about this cluster

Article Content

More articles in this cluster

Attack Flow

Defensive Countermeasures

Extracted Entities

Community

Continue Reading

Tracked Entities in This Story