| Título | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| Descripción | 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.
|
|---|
| Fuente | ⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md |
|---|
| Usuario | Goku (UID 80486) |
|---|
| Sumisión | 2026-03-06 12:58 (hace 7 meses) |
|---|
| Moderación | 2026-03-20 15:40 (14 days later) |
|---|
| Estado | Aceptado |
|---|
| Entrada de VulDB | 352081 [Foundation Agents MetaGPT hasta 0.8.1 DataInterpreter write_analysis_code.py escalada de privilegios] |
|---|
| Puntos | 19 |
|---|