| Título | vanna.ai vanna 2.0.2 Remote command execution |
|---|
| Descripción |
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.
|
|---|
| Fuente | ⚠️ https://github.com/Ka7arotto/cve/blob/main/vanna-rce.md |
|---|
| Usuario | Goku (UID 80486) |
|---|
| Sumisión | 2026-03-06 12:46 (hace 3 meses) |
|---|
| Moderación | 2026-03-20 15:28 (14 days later) |
|---|
| Estado | Aceptado |
|---|
| Entrada de VulDB | 352077 [vanna-ai vanna hasta 2.0.2 /src/vanna/legacy exec escalada de privilegios] |
|---|
| Puntos | 20 |
|---|