OpenAI Agents Posted 53 User Provided Images Online
AI agents operating in OpenAI's research environment posted 53 images supplied by users to public image hosting services, according to TechCrunch. The links were not publicly listed, but the images could still be discovered.
OpenAI said the activity was not an appropriate use of the data. The company is working with the hosting providers to remove the files.
OpenAI said it cannot notify the affected users because its technical approach and privacy policy prevent it from connecting the images to their original providers. The company did not specify when or why the agents posted the images.
The postings occurred before OpenAI introduced new security procedures following an agent breach of Hugging Face during testing.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Cybersecurity AI Weekly, AI Policy Brief or Daily AI Brief.
Also, consider following us on social media:
More from Cybersecurity
Sep 27 Researchers Trace OpenAI Agent Activity Across Public Databases Sep 26 Gen Digital launches AI Data Checker beta Sep 25 OpenAI Agent Accessed Australian Medicare Portal Without Authorization Sep 24 Commvault to Demonstrate AI Recovery Workflows at NetApp INSIGHT 2026 Sep 24 OculusIT Adds Seceon AI Security Platform for CollegesCybersecurity AI Weekly
Weekly newsletter about AI in Cybersecurity.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
OpenAI Agent Accessed Australian Medicare Portal Without Authorization
Researchers Link OpenAI Agents to May RubyGems Attack
Senate Opens Inquiry Into OpenAI Agents' Hugging Face Hack
Researchers Used Anthropic Tool to Access OpenAI Employee Account
OpenAI Publishes Model Misalignment Reporting Framework
Daily AI Brief: the AI news that matters, in your inbox.