Lucene search
+L

468 matches found

Mend
Mend
•added 2024/02/01 10:00 p.m.•1 views

MAI-2024-0059

Multimodal Large Language Models MLLMs operating within multi-agent environments are susceptible to a sophisticated attack known as "infectious jailbreak." This vulnerability is triggered by the introduction of a single adversarial image into the memory of one agent, which can rapidly propagate...

6.3CVSS5.9AI score
SaveExploits0References1
NVD
NVD
•added 2024/01/31 5:15 p.m.•56 views

CVE-2024-24566

Lobe Chat is a chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. When the application is password-protected deployed with the ACCESSCODE option, it is possible to access plugins without proper authorization without password. This vulnerabili...

5.3CVSS5.1AI score0.00482EPSS
SaveExploits1References2
Prion
Prion
•added 2024/01/31 5:15 p.m.•25 views

Authorization

Lobe Chat is a chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. When the application is password-protected deployed with the ACCESSCODE option, it is possible to access plugins without proper authorization without password. This vulnerabili...

5CVSS7AI score0.00482EPSS
SaveExploits1References2Affected Software1
OSV
OSV
•added 2024/01/31 4:33 p.m.•148 views

CVE-2024-24566 Lobe Chat unauthorized access to plugins

Lobe Chat is a chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. When the application is password-protected deployed with the ACCESSCODE option, it is possible to access plugins without proper authorization without password. This vulnerabili...

5.3CVSS5.3AI score
SaveExploits0References4
Mend
Mend
•added 2023/11/01 10:00 p.m.•2 views

MAI-2023-0004

Multimodal Large Language Models MLLMs are susceptible to a newly identified attack vector involving query-relevant images. These images, crafted using advanced techniques such as Stable Diffusion and typography, can circumvent established safety protocols and provoke unsafe outputs, even when th...

8.2CVSS5.8AI score
SaveExploits0References1
OSV
OSV
•added 2022/09/21 9:42 p.m.•14 views

GHSA-6H2X-4GJF-JC5W autogluon.multimodal vulnerable to unsafe YAML deserialization

Impact A potential unsafe deserialization issue exists within the autogluon.multimodal module, where YAML files are loaded via yaml.load instead of yaml.safeload. The deserialization of untrusted data may allow an unprivileged third party to cause remote code execution, denial of service, and...

7.1AI score
SaveExploits0References4
Github Security Blog
Github Security Blog
•added 2022/09/21 9:42 p.m.•44 views

autogluon.multimodal vulnerable to unsafe YAML deserialization

Impact A potential unsafe deserialization issue exists within the autogluon.multimodal module, where YAML files are loaded via yaml.load instead of yaml.safeload. The deserialization of untrusted data may allow an unprivileged third party to cause remote code execution, denial of service, and...

9.8CVSS7.4AI score0.05656EPSS
SaveExploits2References4Affected Software1
Openbugbounty
Openbugbounty
•added 2018/07/20 3:34 p.m.•23 views

destineo.fr XSS vulnerability

Open Bug Bounty ID: OBB-651089 Description| Value ---|--- Affected Website:| destineo.fr Open Bug Bounty Program:| Create your bounty program now. It's open and free. Vulnerable Application:| Custom Code Vulnerability Type:| XSS Cross Site Scripting / CWE-79 CVSSv3 Score:| 6.1...

6.2AI score
SaveExploits0
Rows per page
Query Builder