CVE-2026-6603 modelscope agentscope _python.py execute_shell_command code injection

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 modelscope agentscope _python.py execute_shell_command code injection

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

CVE-2026-6603 affects modelscope agentscope up to version 1.0.18. The vulnerability targets the function execute_python_code/execute_shell_command in src/AgentScope/tool/_coding/_python.py, enabling code injection due to the underlying manipulation. The attack is described as remotely exploitable...

PT-2026-33710

A vulnerability was identified in modelscope agentscope up to 1.0.18. Affected by this issue is the function parse url/prepare image/openai audio to text of the file src/agentscope/tool/ multi modality/ openai tools.py of the component Cloud Metadata Endpoint. Such manipulation of the argument...

PT-2026-33711

A security flaw has been discovered in modelscope agentscope up to 1.0.18. This affects the function get bytes from web url of the file src/agentscope/ utils/ common.py of the component Internal Service. Performing a manipulation results in server-side request forgery. It is possible to initiate...

AgentScope 安全漏洞

AgentScope is an open-source application developed by ModelScope. It simplifies the development of multi-agent applications based on LLMs. Versions of AgentScope prior to 1.0.18 contain security vulnerabilities, which stem from incorrect operations on the function...

AgentScope 安全漏洞

AgentScope is an open-source application developed by ModelScope. It facilitates the simpler development of multi-agent applications based on LLMs. Versions of AgentScope prior to 1.0.18 contained a security vulnerability, which was caused by improper handling of parameters imageurl/audiofileurl ...

PT-2026-33709

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

AgentScope 安全漏洞

AgentScope is an open-source application developed by ModelScope. It simplifies the development of multi-agent applications based on LLMs. Versions of AgentScope prior to 1.0.18 contained a security vulnerability, which was caused by incorrect handling of the parameter url in the file...

GHSA-4GC2-344Q-R2RW MS-Agent vulnerable to Command Injection

A Command Injection vulnerability in ModelScope's MS-Agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

MS-Agent vulnerable to Command Injection

A Command Injection vulnerability in ModelScope's MS-Agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256 Command injection vulnerability in ModelScope's ms-agent

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256 Command injection vulnerability in ModelScope's ms-agent

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

Summary: CVE-2026-2256 affects ModelScope’s ms-agent up to version v1.6.0rc1. The root cause is improper input sanitization in the Shell tool, where a regex-based blacklist can be bypassed, enabling an attacker to run arbitrary OS commands via crafted prompt-derived input. This can lead to full s...

EUVD-2026-9257

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

CVE-2026-2256

A command injection vulnerability in ModelScope's ms-agent versions v1.6.0rc1 and earlier exists, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input...

MS-Agent 安全漏洞

MS-Agent is an open-source personal assistant framework developed by ModelScope. Versions of MS-Agent prior to v1.6.0rc1 contained security vulnerabilities. These vulnerabilities stemmed from specially crafted prompt inputs that could lead to command injection, allowing execution of arbitrary...

PT-2026-22697

Name of the Vulnerable Software and Affected Versions ModelScope ms-agent versions v1.6.0rc1 and earlier Description A command injection flaw exists in ModelScope's ms-agent, allowing an attacker to execute arbitrary operating system commands through crafted prompt-derived input. The vulnerabilit...