Vertex AI Studio data exfiltration

Published Thu, Oct 19th, 2023


In Vertex AI Studio, a Prompt Injection attack could cause the LLM to return markdown tags. This could have allowed an adversary whose data makes it into the chat context (e.g., via an uploaded file) to achieve exfiltration of the victim’s data by rendering hyperlinks. However, the severity of this issue is low, as there were no integrations that could pull remote content. This means Indirect Prompt Injection was not possible, and it would require the victim to copy the malicious prompt from elsewhere. A similar issue affected Azure AI.

Affected Services

Vertex AI Studio


None required

Tracked CVEs

No tracked CVEs


Disclosure Date
Wed, Aug 30th, 2023
Exploitablity Period
Known ITW Exploitation
Detection Methods
Piercing Index Rating
Discovered by
Johann Rehberger