Lucene search
+L

32 matches found

PyPA
PyPA
•added 2026/08/04 11:34 a.m.•32 views

AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK install_packages()

SummaryThe AWS Bedrock AgentCore Python SDK bedrock-agentcore provides tools for building AI agents, including a Code Interpreter client that installs Python packages into a managed sandbox. An issue exists where, under certain circumstances, improper neutralization of argument delimiters in the...

8.4CVSS6.4AI score0.00725EPSS
SaveExploits0References9Affected Software1
EUVD
EUVD
•added 2026/07/24 10:38 p.m.•14 views

EUVD-2026-48422

AWS Bedrock AgentCore: Improper neutralization of argument delimiters in the Python SDK installpackages...

8.4CVSS5.8AI score0.00725EPSS
SaveExploits0References6
NVD
NVD
•added 2026/07/23 9:17 p.m.•23 views

CVE-2026-16796

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

8.4CVSS0.00725EPSS
SaveExploits0References3
attackerkb
attackerkb
•added 2026/07/23 8:06 p.m.•18 views

CVE-2026-16796

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK before 1.18.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate this issue, user...

8.4CVSS6AI score0.00725EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
•added 2026/07/23 12:00 a.m.•50 views

PT-2026-64164

Name of the Vulnerable Software and Affected Versions AWS Bedrock AgentCore Python SDK versions prior to 1.18.1 Description Improper neutralization of argument delimiters in the install packages method allows a remote authenticated user to execute arbitrary commands within the Code Interpreter...

8.4CVSS6.2AI score0.00725EPSS
SaveExploits0References10
OSV
OSV
•added 2026/07/09 4:48 p.m.•22 views

CVE-2026-59216 Open WebUI: Cross-user code-interpreter and tool execution via unvalidated Socket.IO event-caller session_id

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. Prior to 0.10.0, geteventcall delivered execute:python and execute:tool Socket.IO events to a client-supplied sessionid after checking only that the session was connected, allowing authenticated users who learne...

7.7CVSS6.1AI score
SaveExploits0References6
CVE
CVE
•added 2026/07/09 4:48 p.m.•84 views

CVE-2026-59216

Open WebUI prior to 0.10.0 is vulnerable to cross-user code execution via unvalidated Socket.IO event-caller session_id. The get_event_call path delivers execute:python and execute:tool events to a client-supplied session_id after only confirming the session is connected, enabling an attacker who...

9CVSS6AI score0.00454EPSS
SaveExploits0References4Affected Software1
Cvelist
Cvelist
•added 2026/07/09 4:48 p.m.•53 views

CVE-2026-59216 Open WebUI: Cross-user code-interpreter and tool execution via unvalidated Socket.IO event-caller session_id

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. Prior to 0.10.0, geteventcall delivered execute:python and execute:tool Socket.IO events to a client-supplied sessionid after checking only that the session was connected, allowing authenticated users who learne...

7.7CVSS0.00454EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2026/07/09 4:48 p.m.•18 views

CVE-2026-59216 Open WebUI: Cross-user code-interpreter and tool execution via unvalidated Socket.IO event-caller session_id

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. Prior to 0.10.0, geteventcall delivered execute:python and execute:tool Socket.IO events to a client-supplied sessionid after checking only that the session was connected, allowing authenticated users who learne...

7.7CVSS6AI score0.00454EPSS
SaveExploits0References4
Positive Technologies
Positive Technologies
•added 2026/07/09 12:00 a.m.•24 views

PT-2026-56882

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.10.0 Description Authenticated users can execute Python code or tools within another user's session. This occurs because the get event call function delivers execute:python and execute:tool Socket.IO events to a...

9CVSS6.2AI score0.00454EPSS
SaveExploits0References10
EUVD
EUVD
•added 2026/06/19 2:46 p.m.•25 views

EUVD-2026-37802

Improper neutralization of argument delimiters in AWS Bedrock AgentCore Python SDK installpackages...

8.4CVSS5.8AI score0.00342EPSS
SaveExploits0References4
NVD
NVD
•added 2026/06/17 10:16 p.m.•47 views

CVE-2026-12530

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK versions = 1.1.3 and 1.6.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate thi...

8.4CVSS0.00342EPSS
SaveExploits0References2
CVE
CVE
•added 2026/06/17 9:05 p.m.•114 views

CVE-2026-12530

The issue CVE-2026-12530 affects the AWS Bedrock AgentCore Python SDK install_packages() in versions >= 1.1.3 and

8.4CVSS6AI score0.00342EPSS
SaveExploits0References2
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/06/17 12:00 a.m.•1 views

CVE-2026-12530: Improper Neutralization of Argument Delimiters in a Command

Improper neutralization of argument delimiters in the installpackages method in AWS Bedrock AgentCore Python SDK versions = 1.1.3 and 1.6.1 might allow a remote authenticated user to execute arbitrary commands within the Code Interpreter sandbox via crafted package name arguments. To mitigate thi...

8.4CVSS6.4AI score0.00342EPSS
SaveExploits0References2
RedhatCVE
RedhatCVE
•added 2026/03/31 5:01 p.m.•19 views

CVE-2026-2275

The CrewAI CodeInterpreter tool falls back to SandboxPython when it cannot reach Docker, which can enable RCE through arbitrary C function calling...

9.6CVSS6AI score0.00442EPSS
SaveExploits0References1
Snyk
Snyk
•added 2026/03/30 5:28 p.m.•8 views

Exposed Dangerous Method or Function

Overview crewai-tools is a Set of tools for the crewAI framework Affected versions of this package are vulnerable to Exposed Dangerous Method or Function via the CodeInterpreter tool that fallbacks to SandboxPython when Docker is unreachable. An attacker can execute arbitrary code by invoking...

9.6CVSS6.4AI score0.00442EPSS
SaveExploits0References2
NVD
NVD
•added 2026/03/30 4:16 p.m.•17 views

CVE-2026-2275

The CrewAI CodeInterpreter tool falls back to SandboxPython when it cannot reach Docker, which can enable RCE through arbitrary C function calling...

9.6CVSS0.00442EPSS
SaveExploits0References2
CVE
CVE
•added 2026/03/30 3:50 p.m.•67 views

CVE-2026-2275

The crewai-tools package (specifically the CodeInterpreter tool ) is vulnerable to Remote Code Execution (RCE) because it falls back to SandboxPython when it cannot reach a Docker container. This fallback environment fails to block the ctypes module, allowing an attacker to invoke arbitrary C fun...

6AI score0.00442EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/03/30 12:00 a.m.•23 views

PT-2026-29048

Name of the Vulnerable Software and Affected Versions CrewAI versions affected versions not specified Description The CodeInterpreter tool within CrewAI reverts to SandboxPython when Docker is unreachable. This fallback can allow for Remote Code Execution RCE through the ability to call arbitrary...

9.6CVSS6.1AI score0.00442EPSS
SaveExploits0References10
CERT
CERT
•added 2026/03/30 12:00 a.m.•42 views

CrewAI contains multiple vulnerabilities including SSRF, RCE and local file read

Overview Four vulnerabilities have been identified in CrewAI, including remote code execution RCE, arbitrary local file read, and server-side request forgery SSRF. CVE-2026-2275 is directly caused by the Code Interpreter Tool. The other three vulnerabilities result from improper default...

9.8CVSS6.7AI score0.00733EPSS
SaveExploits0References1
Rows per page
Query Builder