CVE-2024-5565
Prompt Injection in "ask" API with visualization leads to RCE
Vexday Risk Score
26Low
SSVC decision (CISA)
Track
No exploitation signal → monitor
CVSS 8.1EPSS 15.0%KEV nãoPoC —Nuclei —Metasploit —Patch —
Lifecycle
31 May 2024Published on NVD
Recommendation: Monitor — no exploitation signal at the moment.
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
vannaWant to know if your infrastructure is exposed to this?
Talk to TrueHacking →