| 标题 | vanna.ai vanna 2.0.2 Remote command execution |
|---|
| 描述 |
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.
|
|---|
| 来源 | ⚠️ https://github.com/Ka7arotto/cve/blob/main/vanna-rce.md |
|---|
| 用户 | Goku (UID 80486) |
|---|
| 提交 | 2026-03-06 12時46分 (3 月前) |
|---|
| 管理 | 2026-03-20 15時28分 (14 days later) |
|---|
| 状态 | 已接受 |
|---|
| VulDB条目 | 352077 [vanna-ai vanna 直到 2.0.2 /src/vanna/legacy exec 权限提升] |
|---|
| 积分 | 20 |
|---|