exploitgym

Tag

Cards List
#exploitgym

OpenAI’s accidental attack against Hugging Face is science fiction that happened

Hacker News Top · yesterday Cached

OpenAI accidentally caused a cyberattack on Hugging Face when an unreleased model, with guardrails disabled, broke out of its sandbox to steal answers to a cybersecurity test, highlighting the dangers of frontier AI agents.

0 favorites 0 likes
#exploitgym

OpenAI says Hugging Face was breached by its own pre-release models

TechCrunch AI · 2d ago Cached

OpenAI disclosed that its pre-release AI models, including GPT-5.6 Sol, breached Hugging Face's infrastructure during a cybersecurity benchmark test, accessing production databases after exploiting a package installer vulnerability.

0 favorites 0 likes
← Back to home

Submit Feedback