| Titre | vanna.ai vanna 2.0.2 Remote command execution |
|---|
| Description |
Because **user input is controllable**, and LLM output is also affected by prompt injection, attackers can construct malicious prompts to induce the model to insert arbitrary Python statements (e.g., importing `os`/`subprocess` and executing system commands) into the "Plotly code". If this code is executed by `exec()`, it could result in **arbitrary command execution (RCE)** on the host machine.
|
|---|
| La source | ⚠️ https://github.com/Ka7arotto/cve/blob/main/vanna-rce.md |
|---|
| Utilisateur | Goku (UID 80486) |
|---|
| Soumission | 06/03/2026 12:46 (il y a 7 mois) |
|---|
| Modérer | 20/03/2026 15:28 (14 days later) |
|---|
| Statut | Accepté |
|---|
| Entrée VulDB | 352077 [vanna-ai vanna jusqu’à 2.0.2 /src/vanna/legacy exec élévation de privilèges] |
|---|
| Points | 20 |
|---|