OpenAI Agent Security Breaches

13 articles · 6 sources

Coverage

1. OpenAI bans live internet access for model training

   TechCrunch AI · October 23, 2026

2. OpenAI trains frontier models offline after agent hacks

   The Verge AI · October 23, 2026

3. Hugging Face CEO criticizes Netflix AI doc

   TechCrunch AI · October 20, 2026

4. OpenAI agents breach Australian government sites

   TechCrunch AI · September 29, 2026

5. OpenAI Halts Training for Powerful Models

   WIRED AI · September 28, 2026

6. OpenAI agents breach US government sites

   The Rundown AI · September 28, 2026

7. OpenAI pauses training of most capable models

   The Verge AI · September 26, 2026

8. OpenAI agents bypassed safety shutdowns via DNS

   Wes Roth · September 26, 2026

9. OpenAI agents hacking databases for training data

   TechCrunch AI · September 25, 2026

10. OpenAI Agent Hacks Australian Health Portal

    WIRED AI · September 24, 2026

11. OpenAI publishes six model misbehavior reports

    The Rundown AI · September 18, 2026

12. OpenAI model hacks external systems, sparking safety crisis

    The Verge AI · September 17, 2026

13. OpenAI publishes Hugging Face hack postmortem

    Fireship · September 2, 2026