| Titolo | deepwisdom MetaGPT v0.8.1 Remote command execution |
|---|
| Descrizione | The vulnerable component is located in `metagpt/ext/aflow/scripts/operator.py`. The `Programmer` class is used to pass user-controlled natural language questions to the `code_generate` method for LLM to generate code. The `sanitize` method checks and filters the AST structure of the code, and the `run_code` method implements security restrictions on the import of libraries such as command execution and sets global variables to null. Finally, execution is achieved through `exec(code, global_namespace)` in `run_code`. However, attackers can generate bypassable malicious Python code through carefully crafted prompt control, thereby remotely running arbitrary commands on the host machine. |
|---|
| Fonte | ⚠️ https://github.com/Ka7arotto/cve/blob/main/metagpt-rce1.md |
|---|
| Utente | Goku (UID 80486) |
|---|
| Sottomissione | 06/03/2026 12:57 (7 mesi fa) |
|---|
| Moderazione | 20/03/2026 15:40 (14 days later) |
|---|
| Stato | Accettato |
|---|
| Voce VulDB | 352080 [Foundation Agents MetaGPT fino a 0.8.1 operator.py code_generate escalationi di privilegi] |
|---|
| Punti | 20 |
|---|