| タイトル | vanna.ai vanna 2.0.2 Remote command execution |
|---|
| 説明 |
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.
|
|---|
| ソース | ⚠️ https://github.com/Ka7arotto/cve/blob/main/vanna-rce.md |
|---|
| ユーザー | Goku (UID 80486) |
|---|
| 送信 | 2026年03月06日 12:46 (7 月 ago) |
|---|
| モデレーション | 2026年03月20日 15:28 (14 days later) |
|---|
| ステータス | 承諾済み |
|---|
| VulDBエントリ | 352077 [vanna-ai vanna 迄 2.0.2 /src/vanna/legacy exec 特権昇格] |
|---|
| ポイント | 20 |
|---|