CyberRota Analysis
AI-GeneratedAgentscope versions 1.0.18, 1.0.19, and 1.0.19 are vulnerable due to the exposure of the execute_python_code function via the RealtimeAgent session, allowing remote WebSocket users to execute arbitrary Python code within the service environment. This vulnerability could lead to unauthorized code execution, potentially compromising the integrity and security of the system. Organizations using affected versions should prioritize remediation to mitigate the risk of exploitation.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
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.