YouTube AI Assistant Vulnerability Exposes Private Video Titles

• •YouTube's Ask Studio AI can be manipulated to leak private video titles via prompt injection.
• •Attackers can embed malicious instructions in comments, leading to unauthorized data exposure.
• •Google has classified the issue as non-security despite the potential for significant information leaks.

A security researcher, Javox, demonstrated that YouTube's Ask Studio AI can be manipulated to leak private video titles through prompt injection. By embedding malicious instructions in the comments section, attackers can trick the AI into revealing sensitive information, including titles of private and draft videos. This vulnerability arises because Ask Studio has access to creators' channel information, allowing it to generate responses that include confidential data. Despite reporting the issue to Google, the company deemed it a non-security issue as it requires user interaction. The potential for exploitation raises concerns about the trust users place in AI assistants. The impact could be significant, as leaked titles may contain sensitive project names or personal records. Google has not taken action to track this as a security risk, leaving creators vulnerable.