Indirect Prompt Injection

Vulnerability

Threat entity extracted from intelligence sources

Frequency

occurrences

First Seen

November 6, 2025

Last Seen

August 20, 2026

API

Indirect Prompt Injection is a vulnerability class where crafted prompts or contextual inputs influence an AI system to reveal sensitive data or bypass guardrails, often without modifying the model itself.

Overview

Recent Events

Related Clusters (4)

Related Entities

Prompt Injection Phishing Data Breach PromptArmor T1567 - Exfiltration Over Web Service T1132 - Data Encoding T1566 - Phishing ChatGPT Aes-256-gcm Base64 Encoding ChatGPT-4o ChatGPT-5

Indirect Prompt Injection

Overview

Recent Events

Profile

Tools Used

MITRE Techniques

Affected Platforms

Related Clusters (4)

New Cryptographic Context Injection Attack Targets AI Coding Agents

ChatGPT for Google Sheets Plugin Exposes Serious Data Exfiltration Risks

Seven Vulnerabilities in ChatGPT Expose User Data to Attack

Seven ChatGPT Vulnerabilities Expose User Data to Theft and Hijacking

Related Articles (4)

Grok chat duped into swallowing injected instructions

Financial Data Crisis! ChatGPT Spreadsheet Plugin Exposes Serious Security Vulnerability

Multiple ChatGPT Security Bugs Allow Rampant Data Theft

Seven ChatGPT flaws expose user data to attack, Tenable warns

Related Entities