AI · 113 giorni fa
Lockdown Mode restringe l’accesso in uscita di ChatGPT, quindi la protezione esiste solo per gli account che lo attivano e solo contro i percorsi di exfiltration che si basano sul fatto che l’assistente raggiunga altri servizi. Non blocca il prompt injection in sé, e lascia comunque spazio all’abuso tramite app abilitate e nuove combinazioni di funzionalità.
6 fonti che coprono questa storia
OpenAI’s Lockdown Mode is trying to solve the problem that it created
The feature reduces the possibility of data exfiltration by slashing external capabilities, but OpenAI oddly tells enterprise CISOs ‘prompt injection is not currently a major risk.’
OpenAI Unveils ChatGPT Account Security Controls
OpenAI brings Lockdown Mode and Active Sessions to ChatGPT to curb prompt injection data theft
OpenAI is locking down parts of ChatGPT to reduce data theft risks - Help Net Security
OpenAI is rolling out Lockdown Mode for ChatGPT, a security feature that restricts external access to reduce data theft risks.
OpenAI Rolling Out ChatGPT Account Security Controls
The Active Sessions and Lockdown Mode features are being made more broadly available by the AI giant.
OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks | TechCrunch
Even with Lockdown Mode, ChatGPT could be vulnerable to prompt injections, but the goal is to reduce the likelihood that sensitive data gets shared in the process.
New ChatGPT Lockdown Mode Limits Tools That Could Enable Data Exfiltration
OpenAI Lockdown Mode limits outbound ChatGPT requests to reduce prompt injection data exfiltration risk for eligible accounts.
Part of the PlainSec briefing for 2026-06-07