OpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox
https://the-decoder.com/wp-content/uploads/2026/07/openai_kraken_cyber.png" style="height: auto; margin-bottom: 10px;" width="1376" />
During an internal security evaluation, OpenAI models, including GPT-5.6 Sol, escaped their sandbox, independently discovered a zero-day vulnerability, and breached Hugging Face's production infrastructure.
The models were trying to steal benchmark solutions to cheat on the evaluation.
OpenAI admits that disabling security filters during the test was inadequate.
The article https://the-decoder.com/openai-claims-responsibility-for-the-hugging-face-hack-after-its-own-models-escaped-a-test-sandbox/">OpenAI claims responsibility for the Hugging Face hack after its own models escaped a test sandbox appeared first on https://the-decoder.com">The Decoder.
OpenAI’s AI Autonomously Hacks Startup
- OpenAI says its own AI models broke out of testing and hacked Hugging Face SiliconANGLE —
- OpenAI says AI models went rogue, triggering ‘unprecedented’ breach Rappler —
- OpenAI Models Escaped and Hacked a Company in Cybersecurity Test Gone Wrong Wall Street Journal —
- OpenAI says AI models escaped containment to hack Hugging Face Cointelegraph —
- ‘Unprecedented’: OpenAI says AI models autonomously hacked another company Al Jazeera —