| Titel | SkyworkAI DeepResearchAgent main OS Command Injection |
|---|
| Beschreibung | Multiple critical Remote Code Execution (RCE) vulnerabilities exist in the DeepResearchAgent project's tool loading system. These vulnerabilities allow arbitrary code execution through insufficient input validation in the `Tool.from_code()`, `Tool.from_dict()`, and `ToolCollection.from_mcp()` methods. When loading tools from external sources, user-controlled input is directly passed to Python's `exec()` function or system command execution without any sanitization or validation, enabling attackers to execute arbitrary code with the privileges of the application process. |
|---|
| Quelle | ⚠️ https://github.com/bayuncao-bit/vul-36 |
|---|
| Benutzer | bayuncao (UID 50143) |
|---|
| Einreichung | 23.07.2025 08:57 (vor 9 Monaten) |
|---|
| Moderieren | 06.08.2025 12:33 (14 days later) |
|---|
| Status | Akzeptiert |
|---|
| VulDB Eintrag | 319026 [SkyworkAI DeepResearchAgent bis 08eb7f8eb9505d0094d75bb97ff7dacc3fa3bbf2 src/tools/tools.py from_code/from_dict/from_mcp erweiterte Rechte] |
|---|
| Punkte | 20 |
|---|