OpenAI Unveils ChatGPT Account Security Controls
ID: cd23766b-7621-5071-bd6e-ccd1f6629c87
STIX ID: report--cd23766b-7621-5071-bd6e-ccd1f6629c87
Feed Name: Infosecurity Magazine (News)
OpenAI introduced Lockdown Mode to limit ChatGPT's outbound network access and mitigate data exfiltration from prompt-injection attacks, and added an Active Sessions feature for users to audit signed-in devices. Lockdown Mode severs exfiltration channels but disables live connectors and write actions; Active Sessions allows session termination but omits SSO accounts, third-party apps and certain CLI logins.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.