Lucene search
+L

23 matches found

CNNVD
CNNVD
•added 2026/10/15 4:00 p.m.•20 views

Duc Minh, Nguyen Arkon – The Open-Source Enterprise AI Knowledge Hub & MCP Server Authorization Vulnerability

Duc Minh, Nguyen Arkon – The Open-Source Enterprise AI Knowledge Hub & MCP Server 0.9.2 and earlier versions have an authorization issue. This vulnerability stems from the lack of an authorization check for the GET /api/wiki/graph interface. Certified employees can access wiki metadata from other...

5.3CVSS5.7AI score0.00251EPSS
SaveExploits0References4
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/21 12:00 a.m.•24 views

CVE-2026-77519: Insufficient Session Expiration

MaxKB is an open-source AI assistant for enterprise. In 2.10.2-lts and earlier, the /chat/api/mcp authentication path looks up an ApplicationApiKey using only its secret and active status, without enforcing the ispermanent and expiretime checks used by the standard chat API. A previously valid,...

5.4CVSS5.9AI score0.0024EPSS
SaveExploits0References2
The Hacker News
The Hacker News
•added 2026/09/12 10:24 a.m.•21 views

When the Whole Company Adopts AI: What It Does to Your SOC

Over the past year, we watched a new class of alert appear in enterprise security operations centers and grow faster than anything else in the stream: alerts that were triggered by AI tools and agents. Not attacks against AI, but the ordinary, everyday footprint of an organization using it, from...

6.1AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/09/02 11:30 a.m.•50 views

How to Secure Enterprise AI: From Adoption to Incident Readiness

The debate about whether AI delivers business value is over. The challenge now is implementing it at scale and securely across every function while meeting board-level pressure to move fast. Organizations must focus on adopting AI at business speed without losing control of cyber risk.Download th...

6.1AI score
SaveExploits0
Akamai Blog
Akamai Blog
•added 2026/08/05 1:00 p.m.•58 views

Shadow AI, Rogue Agents, and Data Leaks: A Special Report on Navigating AI Risk

Discover top enterprise AI risks — from shadow AI to rogue agents and data leaks — plus practical CISO strategies in the new Akamai SOTI special report...

5.5AI score
SaveExploits0
HackRead
HackRead
•added 2026/07/20 12:11 p.m.•45 views

The Hidden Risk in Enterprise AI Agents: Ungoverned Context

Enterprises are handing AI agents real access to customer records, financial systems, internal documents, and the tools that…...

5.4AI score
SaveExploits0
EUVD
EUVD
•added 2026/05/26 8:14 p.m.•40 views

EUVD-2026-31985

MaxKB is an open-source AI assistant for enterprise. Prior to 2.9.1, SSRF via workflowtemplate Import. Authenticated users can supply arbitrary URLs in workflowtemplate.downloadUrl which are fetched server-side without any URL validation or internal IP filtering. This vulnerability is fixed in...

6.3CVSS6.1AI score0.00207EPSS
SaveExploits0References1
EUVD
EUVD
•added 2026/05/26 8:09 p.m.•55 views

EUVD-2026-31983

MaxKB is an open-source AI assistant for enterprise. Prior to 2.8.1, MaxKB v2.8.0 and prior are vulnerable to a server-side request forgery SSRF bypass in the OSS file service URL fetch chat/api/oss/geturl endpoint. The vulnerability exists due to inconsistent URL parsing between the urlparse...

6.3CVSS6AI score0.00232EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
•added 2026/05/26 12:00 a.m.•61 views

PT-2026-43396

Name of the Vulnerable Software and Affected Versions MaxKB versions prior to 2.8.1 Description An issue exists in the OSS file service URL fetch endpoint "chat/api/oss/get url" where inconsistent URL parsing between the urlparse validation function and the requests HTTP client allows for a...

6.3CVSS5.8AI score0.00232EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/05/26 12:00 a.m.•46 views

PT-2026-43398

Name of the Vulnerable Software and Affected Versions MaxKB versions prior to 2.8.1 Description Broken access control exists in the OSS file service URL fetch API endpoint "chat/api/oss/get url". The system uses the application id variable from the URL path without validating ownership, which...

5.3CVSS5.8AI score0.00207EPSS
SaveExploits0References3
Trend Micro Simply Security
Trend Micro Simply Security
•added 2026/03/16 12:00 a.m.•26 views

Securing Autonomous AI Agents with TrendAI & NVIDIA OpenShell

Agentic AI is rapidly redefining how software systems operate. Instead of responding to single prompts, AI agents can now plan tasks, invoke tools, modify their own execution paths, and operate continuously over time. While this shift unlocks powerful new use cases, it also introduces an entirely...

6.2AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/03/03 11:30 a.m.•33 views

AI Agents: The Next Wave Identity Dark Matter - Powerful, Invisible, and Unmanaged

The Rise of MCPs in the Enterprise The Model Context Protocol MCP is quickly becoming a practical way to push LLMs from “chat” into real work. By providing structured access to applications, APIs, and data, MCP enables prompt-driven AI agents that can retrieve information, take action, and automa...

6AI score
SaveExploits0
CVE
CVE
•added 2025/12/11 9:39 p.m.•74 views

CVE-2025-66419

CVE-2025-66419 affects MaxKB: the tool module in versions 2.3.1 and earlier allows an attacker to escape the sandbox and escalate privileges under certain concurrent conditions. Consequences are privilege elevation and potential broader impact within affected deployments. The issue has a fixed re...

10CVSS6AI score0.00333EPSS
SaveExploits0References3Affected Software1
Positive Technologies
Positive Technologies
•added 2025/12/11 12:00 a.m.•29 views

PT-2025-50768

Name of the Vulnerable Software and Affected Versions MaxKB versions prior to 2.4.0 Description MaxKB, an open-source AI assistant for enterprise, contains a flaw in the tool module that allows an attacker to escape the sandbox environment and gain elevated privileges. This occurs under specific...

8.8CVSS6AI score0.00333EPSS
SaveExploits0References6
NVD
NVD
•added 2025/11/13 4:15 p.m.•38 views

CVE-2025-64703

MaxKB is an open-source AI assistant for enterprise. In versions prior to 2.3.1, a user can get sensitive informations by Python code in tool module, although the process run in sandbox. Version 2.3.1 fixes the issue...

6.5CVSS0.00211EPSS
SaveExploits0References1
EUVD
EUVD
•added 2025/11/13 3:52 p.m.•27 views

EUVD-2025-175301

MaxKB is an open-source AI assistant for enterprise. In versions prior to 2.3.1, a user can get sensitive informations by Python code in tool module, although the process run in sandbox. Version 2.3.1 fixes the issue...

6.3CVSS5.8AI score0.00211EPSS
SaveExploits0References1
CVE
CVE
•added 2025/11/13 3:51 p.m.•78 views

CVE-2025-64511

MaxKB is vulnerable in versions prior to 2.3.1 due to SSRF in the tool module’s Python code, which can access internal network services (e.g., databases) even though the process runs in a sandbox. The issue is resolved in version 2.3.1. Connected sources corroborate the sandboxed Python-access pa...

8.8CVSS5.8AI score0.00219EPSS
SaveExploits0References1Affected Software1
EUVD
EUVD
•added 2025/11/13 3:51 p.m.•31 views

EUVD-2025-175302

MaxKB is an open-source AI assistant for enterprise. In versions prior to 2.3.1, a user can access internal network services such as databases through Python code in the tool module, although the process runs in a sandbox. Version 2.3.1 fixes the issue...

7.4CVSS5.8AI score0.00219EPSS
SaveExploits0References1
Positive Technologies
Positive Technologies
•added 2025/11/13 12:00 a.m.•33 views

PT-2025-46859

Name of the Vulnerable Software and Affected Versions MaxKB versions prior to 2.3.1 Description MaxKB, an open-source AI assistant for enterprise, allows a user to access internal network services, such as databases, through Python code within the tool module. This process operates within a sandb...

7.4CVSS6.1AI score0.00219EPSS
SaveExploits0References5
Akamai Blog
Akamai Blog
•added 2025/10/06 1:00 p.m.•14 views

AI Is Now the #1 Data Exfiltration Vector in the Enterprise And Nobody’s Watching

AI technology went from an experimental toy to a workplace staple in under three years. That much we all knew. What nobody expected was how fast it would surpass traditional SaaS categories not only in adoption, but in risk. Our new Enterprise AI and SaaS Data Security Report 2025, based on...

5.9AI score
SaveExploits0
Rows per page
Query Builder