| 标题 | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| 描述 | 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.
|
|---|
| 来源 | ⚠️ https://github.com/Ka7arotto/cve/blob/main/MetaGPT-rce2.md |
|---|
| 用户 | Goku (UID 80486) |
|---|
| 提交 | 2026-03-06 12時58分 (7 月前) |
|---|
| 管理 | 2026-03-20 15時40分 (14 days later) |
|---|
| 状态 | 已接受 |
|---|
| VulDB条目 | 352081 [Foundation Agents MetaGPT 直到 0.8.1 DataInterpreter write_analysis_code.py 权限提升] |
|---|
| 积分 | 19 |
|---|