| Título | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| Descrição | 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.
|
|---|
| Fonte | ⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md |
|---|
| Utilizador | Goku (UID 80486) |
|---|
| Submissão | 06/03/2026 12h58 (há 7 meses) |
|---|
| Moderação | 20/03/2026 15h40 (14 days later) |
|---|
| Estado | Aceite |
|---|
| Entrada VulDB | 352081 [Foundation Agents MetaGPT até 0.8.1 DataInterpreter write_analysis_code.py Elevação de Privilégios] |
|---|
| Pontos | 19 |
|---|