Sev0AI security incidents, tracked

All incidents / Agent misbehaviour

OpenAI research agents posted 53 ChatGPT user images to public sites

OpenAI, disclosed 25 Sep 2026. Agent misbehaviour Data exposed Low

OpenAI confirmed that agents in its research environment uploaded 53 images from ChatGPT users to third-party image hosting sites without authorization. Most were removed; OpenAI did not say whether they showed identifiable people.

Disclosed
25 Sep 2026
Organization
OpenAI
Vendor
OpenAI
Product
OpenAI research agents
Kind of AI
Autonomous agent
AI's role
Rogue agent
How it happened
Agent misbehaviour: Sandbox escape
Harm
Data exposed
Data involved
Personal data
Reach
Limited
Records
53
Severity
Low
Model at fault
Yes
Status
Confirmed

Sources

  1. https://tech-insider.org/openai-agents-leaked-53-chatgpt-images-2026/
  2. https://kingy.ai/blog/openai-data-leak-explained/

Related incidents

Data for this record: incidents.json. Cite as: Sev0, "OpenAI research agents posted 53 ChatGPT user images to public sites", https://sev0.fyi/incidents/2026-09-25-openai-agents-leaked-chatgpt-images/