agentscope
CVEs (4)
| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-51922 | Cri | 0.64 | 9.8 | 0.01 | Oct 2, 2026 | 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. | ||
| CVE-2026-51856 | Cri | 0.64 | 9.8 | 0.00 | Sep 30, 2026 | 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… | ||
| CVE-2026-51568 | Hig | 0.53 | 8.1 | 0.00 | Sep 30, 2026 | modelscope Agentscope v1.0.18-v1.0.0 is vulnerable to Path Traversal in write_text_file. | ||
| CVE-2026-85685 | Hig | 0.42 | 7.5 | 0.01 | Sep 4, 2026 | 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… |
- risk 0.64cvss 9.8epss 0.01
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.
- risk 0.64cvss 9.8epss 0.00
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…
- risk 0.53cvss 8.1epss 0.00
modelscope Agentscope v1.0.18-v1.0.0 is vulnerable to Path Traversal in write_text_file.
- risk 0.42cvss 7.5epss 0.01
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…