AgentScope是ModelScope开源的一个应用程序。更简单地构建基于 LLM 的多智能体应用。 AgentScope 1.0.18及之前版本存在安全漏洞,该漏洞源于对文件src/agentscope/tool/_multi_modality/_openai_tools.py中参数image_url/audio_file_url的错误操作,可能导致服务端请求伪造。
Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 |
|---|---|---|---|---|
| modelscope | agentscope | 1.0.0 |
cpe:2.3:a:modelscope:agentscope:*:*:*:*:*:*:*:*
|
|
| # | POC Description | Source Link | Shenlong Link |
|---|
No public POC found.
Login to generate AI POC| CVE-2026-6606 | 7.3 HIGH | modelscope agentscope _agent_base.py _process_audio_block server-side request forgery |
| CVE-2026-6605 | 7.3 HIGH | modelscope agentscope Internal Service _common.py _get_bytes_from_web_url server-side requ |
| CVE-2026-6603 | 7.3 HIGH | modelscope agentscope _python.py execute_shell_command code injection |
No comments yet