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.
References
Configurations
No configuration.
History
03 Jul 2024, 02:09
Type | Values Removed | Values Added |
---|---|---|
CWE | CWE-94 | |
Summary |
|
31 May 2024, 15:15
Type | Values Removed | Values Added |
---|---|---|
New CVE |
Information
Published : 2024-05-31 15:15
Updated : 2024-07-03 02:09
NVD link : CVE-2024-5565
Mitre link : CVE-2024-5565
CVE.ORG link : CVE-2024-5565
JSON object : View
Products Affected
No product.
CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')