OpenAI Rolls Out Lockdown Mode to Block Prompt-Injection Exfiltration in ChatGPT

OpenAI

Tools official + media 3 src. ~1 min

OpenAI launched Lockdown Mode on June 5, 2026 — an optional advanced security setting that restricts ChatGPT's outbound network capabilities (web browsing, Deep Research, Agent Mode, file downloads) to block data exfiltration via prompt injection attacks. Available to all logged-in personal accounts (Free, Plus, Pro) and self-serve ChatGPT Business. A companion Elevated Risk label surfaces across ChatGPT, ChatGPT Atlas, and Codex to flag high-risk operations.

Why it matters

Prompt injection is the dominant attack vector against LLM-based agents handling sensitive data; Lockdown Mode is the first deterministic, user-controlled mechanism from a major lab that eliminates the exfiltration leg of the attack chain.

Importance: 3/5

Official OpenAI announcement; independent coverage by Engadget and Simon Willison; first deterministic anti-exfiltration control from a major AI lab.

Sources