Lockdown Mode

berlianta 29 points 13 comments June 06, 2026
help.openai.com · View on Hacker News

Discussion Highlights (5 comments)

varenc

Probably influenced by Apple's feature with the same name: https://support.apple.com/en-us/105120 I imagine that enterprise companies will be quite interested in this.

rafram

https://x.com/sama/status/1891533802779910471

kijin

So we still don't have a reliable way to separate instructions from data when talking to an LLM, a problem that humans learned how to solve decades ago in areas like SQL and memory safety. But hey, we have these hopefully-not-leaky containers, which are probably implemented with just more system prompts. How long until somebody figures out how to trick Codex into disabling Lockdown Mode for you?

madanparas

The help doc explicitly carves out Codex: "Lockdown Mode does not affect network access in Codex." The mode limits outbound requests in chat to block prompt injection exfiltration, but Codex network access is a separate setting. An enterprise team that turns on Lockdown Mode while using Codex against internal repos still has an open outbound path this mode doesn't cover.

simonw

On the one hand this is exactly the right solution to prevent lethal trifecta exfiltration attacks. The existence of lockdown mode does however imply that ChatGPT, in its default settings, does not provide robust protection against sufficiently determined data exfiltration attacks!

Semantic search powered by Rivestack pgvector
10,002 stories · 93,925 chunks indexed