Skip to content
Hacker News front page

A single comment can make YouTube's AI assistant leak private video titles

Leaking YouTube Creators Private Videos

A researcher found that YouTube Studio's AI assistant, Ask Studio, reads video comments to generate summaries, but instructions hidden in comments can hijack its output. An attacker leaves a normal comment, later edits it into a payload, and when the creator clicks a suggested prompt, the AI outputs attacker-controlled text. The payload can craft a link that exfiltrates private video titles to an external server. Google dismissed it as not a security bug, citing required social engineering. The researcher argues the exploited trust is in Google's own product, not a stranger. The post does not disclose affected creator or channel counts.

Why it matters: A security researcher found YouTube's AI assistant can be hijacked by instructions in comments, exposing how creator tools blur outside user content with trusted instructions.

Read the original ↗Export Markdown