| शीर्षक | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| विवरण | 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.
|
|---|
| स्रोत | ⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md |
|---|
| उपयोगकर्ता | Goku (UID 80486) |
|---|
| सबमिशन | 06/03/2026 12:58 PM (7 महीनों पहले) |
|---|
| संयम | 20/03/2026 03:40 PM (14 days later) |
|---|
| स्थिति | स्वीकृत |
|---|
| VulDB प्रविष्टि | 352081 [Foundation Agents MetaGPT तक 0.8.1 DataInterpreter write_analysis_code.py अधिकार वृद्धि] |
|---|
| अंक | 19 |
|---|