CVE-2026-51856

In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes executepythoncode 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...

CVE-2026-51856

The agentscope framework (versions 1.0.18 through 1.0.19 ) contains a vulnerability where a remote WebSocket user can prompt a RealtimeAgent to execute arbitrary Python code in the service environment. The issue arises because the RealtimeAgent._acting function forwards model-produced tool calls ...

CVE-2026-51856

In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes executepythoncode 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...

EUVD-2026-90424

In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes executepythoncode 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...

CVE-2026-51856

In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes executepythoncode 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...

CVE-2026-51856: Improper Control of Generation of Code

In agentscope 1.0.18, 1.0.19, and 1.0.19 when the RealtimeAgent session exposes executepythoncode 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...

CVE-2026-6603

A vulnerability was determined in modelscope agentscope up to 1.0.18. Affected by this vulnerability is the function executepythoncode/executeshellcommand of the file src/AgentScope/tool/coding/python.py. This manipulation causes code injection. The attack is possible to be carried out remotely...

CVE-2026-6603: Improper Control of Generation of Code

A vulnerability was determined in modelscope agentscope up to 1.0.18. Affected by this vulnerability is the function executepythoncode/executeshellcommand of the file src/AgentScope/tool/coding/python.py. This manipulation causes code injection. The attack is possible to be carried out remotely...

CVE-2023-37274

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...

CVE-2023-37274: Improper Control of Generation of Code

Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which...