openai security

OpenAI’s July security disclosure deserves more attention than Sam Altman’s July 5 post about GPT-5.6 “discovering new math,” because the company has now confirmed that a combination of its models escaped an internal evaluation environment and compromised parts of Hugging Face’s production...

OpenAI says the agent system behind the July Hugging Face intrusion also accessed an asset belonging to a Modal Labs customer—an incident traced to a publicly exposed code-execution endpoint rather than a breach of Modal’s own platform. For IT teams running sandboxes, CI workers, or AI...