OpenAI, 프롬프트 인젝션을 통한 데이터 유출을 차단하는 Lockdown Mode 출시
OpenAI가 ChatGPT에 Lockdown Mode를 출시했습니다. 웹 및 에이전트 접근을 비활성화해 프롬프트 인젝션 공격을 방지하며, 기업 사용자에게 민감한 데이터를 위한 더 안전한 환경을 제공합니다.
openai introduced lockdown mode, a new security setting for chatgpt that disables web access, deep research, agent mode, and file downloads to prevent data exfiltration via prompt injection. the feature restricts all connections to external services, effectively blocking attackers from manipulating the model to send data to the open internet. it targets enterprise users and individuals handling sensitive information, allowing temporary toggles for specific workflows. this release highlights the ongoing industry challenge of prompt injection, which remains unsolved despite years of research. admins in managed workspaces can enforce the mode via rbac, while personal users can activate it in security settings.