Prompt Injection in "ask" API with visualization leads to RCE
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| affected |
|
No data.
No data.
No data available yet.
| Source | ID | Title |
|---|---|---|
EUVD |
EUVD-2024-1479 | 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. |
Github GHSA |
GHSA-7735-w2jp-gvg6 | Vanna prompt injection code execution |
No CVSS v4.0
No CVSS v3.0
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: 15.2% (15.178% probability within 30 days)
| Type | Values Removed | Values Added |
|---|---|---|
| Metrics |
epss
|
epss
|
| Type | Values Removed | Values Added |
|---|---|---|
| First Time appeared |
Vanna-ai
Vanna-ai vanna |
|
| CPEs | cpe:2.3:a:vanna-ai:vanna:-:*:*:*:*:*:*:* | |
| Vendors & Products |
Vanna-ai
Vanna-ai vanna |
|
| Metrics |
ssvc
|