Investigating three real-world incidents in our cybersecurity evaluations

Investigating three real-world incidents in our cybersecurity evaluations In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened,

[rgfx]

えぐ

[Lian]

PyPIにマルウェア公開とか怖すぎる

[toritaro]

評価環境のClaudeが実在3組織の本番インフラへ不正アクセス。141,006ランの見直しで3件特定。Anthropicは7/23に全サイバー評価を停止、7/27に3組織へ通知

[ytRino]

やりたいほうだいすぎる

[sea295x2]

隠してたけどOpenAIの流れに乗じて出したようにしか見えない　こいつまじでCloseAIやろ

[nguyen-oi]

Claudeが評価環境からネットに出て他社本番環境を攻撃しちゃった件、プロンプトで「ネット接続なし」と嘘ついてたのが一番味わい深い