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

2024-05-3114:24:21

JFROG

github.com

cve-2024-5565

prompt injection

ask api

visualization

rce

vanna library

prompt function

python code

remote code execution

CVSS3

8.1

Attack Vector

NETWORK

Attack Complexity

HIGH

Privileges Required

NONE

User Interaction

NONE

Scope

UNCHANGED

Confidentiality Impact

HIGH

Integrity Impact

HIGH

Availability Impact

HIGH

CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

AI Score

Confidence

High

EPSS

Percentile

9.0%

SSVC

Exploitation

poc

Automatable

Technical Impact

total

JSON

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.

ADP Affected

[
  {
    "cpes": [
      "cpe:2.3:a:vanna-ai:vanna:-:*:*:*:*:*:*:*"
    ],
    "vendor": "vanna-ai",
    "product": "vanna",
    "versions": [
      {
        "status": "affected",
        "version": "-"
      }
    ],
    "defaultStatus": "unknown"
  }
]