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

OpenAI ChatGPT Atlas BioShocking fix

Advisory/Mitigation
H score34 First: 01.07.2026 00:50 Last: 01.07.2026 00:50 Sources 1

About this happening: OpenAI delivered a working fix for BioShocking in ChatGPT Atlas, closing a prompt-injection path that could push an AI browser toward unsafe real-world actions and c...

OpenClaw message-object prompt injection patched in 2026.4.23 security flaw

Vulnerability
H score15 First: 11.06.2026 20:46 Last: 11.06.2026 20:46 Sources 1

About this happening: OpenClaw has a patched message-object prompt injection flaw that let hidden instructions inside shared contacts, vCards, and location pins reach the LLM as trusted pro...

OpenAI ChatGPT Lockdown Mode rollout limits prompt-injection exfiltration paths

Security Tool/Service
H score10 First: 06.06.2026 16:36 Last: 06.06.2026 16:36 Sources 1

About this happening: OpenAI ChatGPT is rolling out Lockdown Mode for eligible personal accounts, reducing the risk of prompt-injection-driven data exfiltration. The update adds stricter li...

OpenAI ChatGPT renderer Markdown link/image phishing security flaw

Vulnerability
H score16 First: 29.05.2026 21:07 Last: 29.05.2026 21:07 Sources 1

About this happening: ChatGPT has a response-renderer vulnerability that turns summarized third-party pages into live phishing links and auto-fetched attacker-hosted images inside the t...

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

Vulnerability
H score33 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...

Timeline

  1. 08.01.2026 18:45 2 articles · 6mo 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