CVE-2026-51922
UnknownSummary
AgentScope v1.0.20 contains a code injection vulnerability in the execute_shell_command function in src/agentscope/tool/_coding/_shell.py. Depending on the exposed entry point, an attacker can trigger attacker-controlled code or command execution.
Risk Assessment
The risk is the potential for remote code or command execution in the application context, which could lead to system compromise or data breach.
Recommendation
It is recommended to immediately update AgentScope to the latest version if available, and restrict access to entry points that can invoke the vulnerable function.
Other vulnerabilities in AgentScope
See all- CVE-2026-51856Critical
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.
- CVE-2026-85685High
AgentScope through 2.0.7.post1 contains a path traversal vulnerability in LocalWorkspace.add_skill that copies arbitrary server directories into the agent workspace via an unconfined source path parameter. Attackers can supply any directory path in the skill_path request parameter to copy files into the skills directory, making them accessible through the workspace skill listing.
Original NVD description (English source)
agentscope v1.0.20 contains code injection in execute_shell_command (src/agentscope/tool/_coding/_shell.py). Depending on the exposed entry, an attacker can trigger attacker-controlled code or command execution.
Vulnerability data from NVD (NIST) · CISA KEV · EPSS