OpenAI rogue agents leaked 53 images from ChatGPT users and reportedly created nearly 1 million links packing encoded bits of info

Fortune•Sat, Sep 26, 2026, 01:16 AM•2 min read

Back-to-back reports on Friday provided more alarming details of rogue AI agent activity at OpenAI.

Source: [Fortune](https://fortune.com/2026/09/25/openai-rogue-agents-images-sam-altman-chatgpt-users-links-encoded-info-hugging-face-hack/)

📰 Read Full Story

This is an aggregated headline summary. For the complete report, visit the original publisher.

Continue Reading at Fortune ↗

#ai #openai #rogue #agents #leaked #images #chatgpt #users #reportedly

More Headlines

AI & MLSeeking Alpha• 48m ago

Akamai: Deal With Anthropic Boosts Existing AI-Driven Tailwind, But Risks Cloud Horizon

Developing story — details emerging. Check the source link for the latest updates.

AI & MLHacker News• 1h ago

OpenAI says agents leaked 53 images from ChatGPT users

3 points, 0 comments on Hacker News

FinanceInvesting.com• 1h ago

Iran awaits US response to Hormuz peace plan as Trump reportedly rejects deal

Developing story — details emerging. Check the source link for the latest updates.

WorldGuardian International• 1h ago

Which story was inspired by rogue waves hitting the Queen Mary? The Saturday quiz

From the Battle of Watling Street and dingo dollars to Atomic Monster, Hammer and Troma, test your knowledge with the Saturday quiz 1 Which diarist was born on 2 April 1967? 2 Which No 1 hit was a tribute to the most recorded female singer of all time? 3 What type of fossils does an ichnologist...

AI & MLInvesting.com• 1h ago

OpenAI agents access US government websites after tests go awry

Developing story — details emerging. Check the source link for the latest updates.

TechnologyHacker News• 1h ago

Can AI Shopping Agents Be Trusted?

14 points, 26 comments on Hacker News