Vulnerability · Published May 31, 2024 · Assigned by JFROG
CVE-2024-5565Prompt Injection in "ask" API with visualization leads to RCE
High 8.1
In plain English
A high-severity code injection in vanna. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 15.2% (higher than 97% of all known vulnerabilities).
Severity (CVSS 3.1)8.1High
Exploit odds (30 days)15.2%top 3.2% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official 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 packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | vanna | no fix listed | GHSA-7735-w2jp-gvg6 |
| PyPI | vanna | no fix listed | PYSEC-2026-561 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| vanna | 0 |
Weakness: CWE-94 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H