CVE-2024-5565: Prompt Injection in "ask" API with visualization leads to RCE

Severity: high (CVSS 8.1 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 15.2% probability of exploitation in the next 30 days
Public exploit or detection template: none known
Published: 2024-05-31 · updated 2026-06-17
Weakness: CWE-94

Description

The Vanna library uses a prompt function to present the user with visualized results, it is possible to alter the prompt using prompt injection and run arbitrary Python code instead of the intended visualization code. Specifically - allowing external input to the library’s “ask” method with "visualize" set to True (default behavior) leads to remote code execution.

Affected products

vanna-ai vanna: all versions

References

https://research.jfrog.com/vulnerabilities/vanna-prompt-injection-rce-jfsa-2024-001034449/
https://research.jfrog.com/vulnerabilities/vanna-prompt-injection-rce-jfsa-2024-001034449/

Get alerted when CVE-2024-5565 or the next vulnerability affects your stack