OpenAI unveils Lockdown Mode to protect sensitive data from prompt injection attacks
ID: 6a7a0a01-2254-56f2-a7da-d56d30d913f9
STIX ID: report--6a7a0a01-2254-56f2-a7da-d56d30d913f9
Feed Name: TechCrunch Security News
OpenAI announced a new Lockdown Mode for ChatGPT aimed at reducing prompt injection and data exfiltration risks by disabling live web browsing, retrieval of web images, deep research, and agent mode for eligible accounts; the company notes the feature reduces but does not eliminate prompt injection risk and is targeted at users handling sensitive data.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.