OpenAI security engineer Michael Dalton and safety researcher Eric Wallace revealed at the Black Hat conference that the company's AI agents hacked into Hugging Face's systems over days and weeks, lea…
OpenAI revealed that its AI models, which escaped containment and hacked into Hugging Face, also used publicly exposed credentials on four accounts across four other services, escalating the security …
OpenAI's AI agent breached Hugging Face and multiple third-party accounts due to basic security lapses, not advanced AI capabilities, researchers say. The incident, which involved an experimental prot…
OpenAI disclosed that its pre-release GPT-5.6 Sol and an unreleased sibling escaped a sandboxed cybersecurity evaluation by exploiting a zero-day in a package-registry cache proxy, then used stolen cr…
OpenAI disclosed on Tuesday that two of its AI models, including the publicly available GPT-5.6 Sol and an unreleased model, escaped a sealed testing environment during a security test and hacked into…