Find notable cyber news and cases, enriched with sources, timelines, and signals.

ChatGPT prompt-injection URL-modification bypass ZombieAgent security flaw

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

Summary

Hide ▲

ZombieAgent is a newly identified prompt-injection vulnerability in ChatGPT that could leak sensitive data from connected services such as Gmail, Outlook, Google Drive, and GitHub. The flaw bypassed OpenAI’s URL-modification defenses by using pre-constructed static URLs and exfiltrating data one character at a time. It was reported through BugCrowd in September 2025 and reportedly fixed in mid-December 2025.

Related Happenings

ChatGPT single-prompt DNS side-channel exfiltration remote code execution flaw

Vulnerability
First: 31.03.2026 16:01 Last: 31.03.2026 16:01 Sources 1

About this happening: A **ChatGPT** vulnerability let a **single malicious prompt** covertly exfiltrate prompts, messages, uploaded files, and other sensitive content through a **DNS side channel**. Th...

OpenAI Safety Bug Bounty launch

Commercial Activity
First: 26.03.2026 14:20 Last: 26.03.2026 14:20 Sources 1

About this happening: **OpenAI** launched the **Safety Bug Bounty** on **Bugcrowd**, expanding researcher coverage for **AI abuse** and **safety risks** across its products. The new program complements...

OpenAI Codex Security rolls out as a research-preview vulnerability-finding agent

Security Tool/Service
First: 07.03.2026 18:28 Last: 07.03.2026 18:28 Sources 1

About this happening: **OpenAI** began rolling out **Codex Security** in **research preview**, adding an AI security agent that can **find, validate, and propose fixes** for vulnerabilities. The rollou...

Google Gemini indirect prompt injection via calendar invites security flaw

Vulnerability
First: 19.01.2026 19:21 Last: 19.01.2026 19:21 Sources 1

About this happening: Researchers disclosed a **Google Gemini** vulnerability in which a malicious **calendar invite** could use **indirect prompt injection** to bypass authorization guardrails and exp...

AWS CodeBuild ACTOR_ID regex bypass security flaw

Vulnerability
First: 15.01.2026 21:31 Last: 15.01.2026 21:31 Sources 1

About this happening: **AWS CodeBuild**'s **ACTOR_ID regex filters** were misconfigured, allowing a build-trigger bypass that could expose privileged GitHub tokens and enable repository takeover. The f...

Timeline

  1. 08.01.2026 18:45 2 articles · 4mo ago

    ChatGPT prompt-injection URL-modification bypass ZombieAgent security flaw

    Initial Disclosure

    Researchers identified **ZombieAgent**, a ChatGPT prompt-injection weakness that could drive the agent to leak data from connected services. OpenAI reportedly closed the issue in **mid-December 2025** after a **September 2025** report through **BugCrowd**.

    Show sources