Lucene search
+L

217 matches found

CNNVD
CNNVD
•added 2026/04/20 12:00 a.m.•24 views

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 ...

7.5CVSS7.1AI score0.00472EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
•added 2026/04/20 12:00 a.m.•20 views

PT-2026-33710

Name of the Vulnerable Software and Affected Versions modelscope agentscope versions prior to 1.0.19 Description An issue exists in the Cloud Metadata Endpoint component within the file src/agentscope/tool/ multi modality/ openai tools.py. Specifically, the functions parse url, prepare image, and...

7.5CVSS6.9AI score0.00472EPSS
SaveExploits0References11
CNNVD
CNNVD
•added 2026/04/20 12:00 a.m.•25 views

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...

7.5CVSS7.2AI score0.00516EPSS
SaveExploits0References1
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/04/20 12:00 a.m.•3 views

CVE-2026-6606: Server-Side Request Forgery (SSRF)

A weakness has been identified in modelscope agentscope up to 1.0.18. This vulnerability affects the function processaudioblock of the file src/agentscope/agent/agentbase.py. Executing a manipulation of the argument url can lead to server-side request forgery. It is possible to launch the attack...

7.5CVSS6.8AI score0.00472EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/04/20 12:00 a.m.•2 views

CVE-2026-6604: Server-Side Request Forgery (SSRF)

A vulnerability was identified in modelscope agentscope up to 1.0.18. Affected by this issue is the function parseurl/prepareimage/openaiaudiototext of the file src/agentscope/tool/multimodality/openaitools.py of the component Cloud Metadata Endpoint. Such manipulation of the argument...

7.5CVSS6.8AI score0.00472EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/04/20 12:00 a.m.•37 views

PT-2026-33711

Name of the Vulnerable Software and Affected Versions modelscope agentscope versions prior to 1.0.19 Description A flaw in the Internal Service component allows for server-side request forgery, which is a condition where an attacker can induce the server to make requests to an unintended location...

7.5CVSS6.9AI score0.00513EPSS
SaveExploits0References11
Positive Technologies
Positive Technologies
•added 2026/04/20 12:00 a.m.•26 views

PT-2026-33709

Name of the Vulnerable Software and Affected Versions modelscope agentscope versions prior to 1.0.19 Description A code injection flaw exists that allows remote attackers to execute arbitrary code. The issue is located in the execute python code and execute shell command functions within the...

7.5CVSS7.2AI score0.00516EPSS
SaveExploits0References11
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/04/20 12:00 a.m.•1 views

CVE-2026-6603: Improper Control of Generation of Code

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...

7.5CVSS6.8AI score0.00516EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/04/20 12:00 a.m.•3 views

CVE-2026-6605: Server-Side Request Forgery (SSRF)

A security flaw has been discovered in modelscope agentscope up to 1.0.18. This affects the function getbytesfromweburl 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 the...

7.5CVSS6.7AI score0.00513EPSS
SaveExploits0References2
OSV
OSV
•added 2026/03/02 9:31 p.m.•17 views

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...

6.5CVSS6.2AI score0.01639EPSS
SaveExploits2References6
Github Security Blog
Github Security Blog
•added 2026/03/02 9:31 p.m.•25 views

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...

6.5CVSS8.5AI score0.01639EPSS
SaveExploits2References7Affected Software1
NVD
NVD
•added 2026/03/02 9:16 p.m.•23 views

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...

6.5CVSS0.01639EPSS
SaveExploits2References5
attackerkb
attackerkb
•added 2026/03/02 8:09 p.m.•17 views

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...

6.5CVSS6.2AI score0.01639EPSS
SaveExploits2References5
Cvelist
Cvelist
•added 2026/03/02 8:09 p.m.•57 views

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...

0.01639EPSS
SaveExploits2References4
OSV
OSV
•added 2026/03/02 8:09 p.m.•19 views

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...

6.5CVSS7.6AI score
SaveExploits0References7
Vulnrichment
Vulnrichment
•added 2026/03/02 8:09 p.m.•9 views

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...

8.5AI score0.01639EPSS
SaveExploits2References4
CVE
CVE
•added 2026/03/02 8:09 p.m.•102 views

CVE-2026-2256

ModelScope's MS-Agent (specifically version v1.5.2 and earlier, including v1.6.0rc1 ) is vulnerable to a command injection flaw in its Shell tool component. The root cause is the improper sanitization of user-influenced input, which is passed directly to a shell execution context at ms_agent/tool...

6.5CVSS8.7AI score0.01639EPSS
SaveExploits2References5
EUVD
EUVD
•added 2026/03/02 8:09 p.m.•33 views

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...

6.2AI score0.01639EPSS
SaveExploits2References4
Positive Technologies
Positive Technologies
•added 2026/03/02 12:00 a.m.•25 views

PT-2026-22697

Name of the Vulnerable Software and Affected Versions ModelScope ms-agent versions prior to v1.6.0rc1 Description A command injection issue exists in the ModelScope ms-agent framework, specifically within the Shell tool, due to improper input sanitization. The regular expression-based blacklist...

6.5CVSS7.4AI score0.01639EPSS
SaveExploits2References42
CNNVD
CNNVD
•added 2026/03/02 12:00 a.m.•21 views

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...

6.5CVSS7.7AI score0.01639EPSS
SaveExploits2References5
Rows per page
Query Builder