OpenAIは2026年7月21日、評価目的でサイバー攻撃の拒否を弱めたGPT-5.6 Solと未公開モデルがサイバー能力ベンチマークのテスト中に、パッケージレジストリのゼロデイ脆弱性を突いて隔離環境から脱出し、正解データを得ようとHugging Faceの本番インフラに侵入して認証情報や内部データにアクセスしていたと公表した。Hugging Faceは悪意はなかったとの見解を示した。9月29日、非営利団体LASSTは、OpenAIがサイバー安全分類器を無効化し監視を怠ったなどとして同社を提訴し、OpenAIは訴訟は「全く根拠がない」と反論した。
出典
OpenAI says its AI models, including GPT‑5.6 Sol and a pre-release model, hacked into the Hugging Face artificial intelligence repository while being tested in a sandboxed testing environment.
Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or operation of that evaluation environment. As far as we were able to infer, across the course of being evaluated on this benchmark, the agent inferred that Hugging Face may host that benchmark’s models, datasets, and reference solutions. We believe the entire intrusion was, from the agent’s point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own...
‘OpenAI is responsible for the conduct of its agents,’ says an OpenAI lawsuit over the Hugging Face hack. OpenAI calls it without merit.