Remote Code Execution via Prompt Injection in vanna-ai/vanna
Default status is the baseline for the product, each version can override it (e.g. patched versions marked unaffected).
| Vendor | Product | Default status | Versions | ||||||
|---|---|---|---|---|---|---|---|---|---|
| vanna-ai | vanna-ai/vanna | affected |
|
No data.
No data.
| Vendor | Product | Versions |
|---|---|---|
| Vanna-ai | Vanna | — |
| Source | ID | Title |
|---|---|---|
EUVD |
EUVD-2024-2162 | In the latest version of vanna-ai/vanna, the `vanna.ask` function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the `exec` function in `src/vanna/base/base.py`. This vulnerability can be exploited by an attacker to achieve remote code execution on the app backend server, potentially gaining full control of the server. |
Github GHSA |
GHSA-rrqq-fv6m-692m | vanna vulnerable to remote code execution caused by prompt injection |
No CVSS v4.0
No CVSS v3.1
No CVSS v2
This CVE is not in the KEV list.
Exploit prediction score: < 1% (0.882% probability within 30 days)
Key SSVC decision points have not yet been added.
No history.