Prompt Injection in "ask" API with visualization leads to RCE
26Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.1epss 15%
exploitation probability
15%top 3% of all CVEs
observed exploitation
nono source reports it
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.
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
Affected products
vanna