In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes execute_python_code as an available tool, a remote WebSocket user can prompt the agent to call that tool and run Python code in the service environment. In the validated path, RealtimeAgent._acting forwards the model-produced tool call to Toolkit.call_tool_function, which invokes execute_python_code without an additional approval or isolation boundary on that path.
References
Configurations
No configuration.
History
01 Oct 2026, 17:17
| Type | Values Removed | Values Added |
|---|---|---|
| References | () https://gist.github.com/Ro1ME/c383f66d1fd6de40b6693f9b6cc181e7 - | |
| CWE | CWE-94 | |
| CVSS |
v2 : v3 : |
v2 : unknown
v3 : 9.8 |
30 Sep 2026, 21:17
| Type | Values Removed | Values Added |
|---|---|---|
| New CVE |
Information
Published : 2026-09-30 21:17
Updated : 2026-10-01 17:17
NVD link : CVE-2026-51856
Mitre link : CVE-2026-51856
CVE.ORG link : CVE-2026-51856
JSON object : View
Products Affected
No product.
CWE
CWE-94
Improper Control of Generation of Code ('Code Injection')
