| عنوان | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| الوصف | A Remote Code Execution (RCE) vulnerability exists in the MetaGPT framework's DataInterpreter component due to insufficient input validation on user-provided prompts. An attacker can use prompt injection to manipulate the LLM into generating malicious Python code, which is then automatically executed in a Jupyter Notebook environment without any sandbox restrictions or security checks.
|
|---|
| المصدر | ⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md |
|---|
| المستخدم | Goku (UID 80486) |
|---|
| ارسال | 06/03/2026 12:58 PM (7 أشهر منذ) |
|---|
| الاعتدال | 20/03/2026 03:40 PM (14 days later) |
|---|
| الحالة | تمت الموافقة |
|---|
| إدخال VulDB | 352081 [Foundation Agents MetaGPT حتى 0.8.1 DataInterpreter write_analysis_code.py تجاوز الصلاحيات] |
|---|
| النقاط | 19 |
|---|