在 agentscope-ai AgentScope(版本 2.0.11 及之前)中发现了一个安全漏洞。受影响的组件是 MCP Workspace API,具体位于文件 中的 函数。攻击者可通过操控 参数引发操作系统命令注入。该攻击可远程发起,且利用方法已公开,可被实际利用。目前,修复此问题的拉取请求(Pull Request)尚待审核接受。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.
| Vendor | Product | Affected Versions | CPE | Subscribe |
|---|---|---|---|---|
| agentscope-ai | AgentScope | 2.0.0 |
cpe:2.3:a:agentscope-ai:agentscope:*:*:*:*:*:*:*:*
|
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-123023 | 7.3 HIGH | agentscope-ai AgentScope Bash Tool _bash.py check_permissions authorization |
| CVE-2026-123024 | 7.3 HIGH | agentscope-ai AgentScope Agent Service deps.py get_current_user_id missing authentication |