Hackers Abuse OpenAI Org Invites to Harvest Sensitive Prompts and API Activity – CyberSecurityNews

Cybersecurity researchers have identified a vulnerability in OpenAI’s organization invitation system that allows hackers to harvest sensitive information, including user prompts and API activity data. Threat actors are exploiting the org invite feature to gain unauthorized access to confidential user interactions and technical details from OpenAI accounts. The discovery highlights potential risks associated with the sharing and invitation mechanisms in enterprise AI platforms.

Read Full Article →