Lucene search
+L

9 matches found

Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/09/04 12:00 a.m.•3 views

CVE-2026-85700: Insufficiently Protected Credentials

Onyx 4.6.6 fails to properly restrict access to custom tool credentials stored in customheaders, allowing any authenticated user to read admin-defined API keys. Attackers with basic authentication can call GET /tool/toolid or GET /tool endpoints to retrieve plaintext authorization headers and...

7.1CVSS5.7AI score0.00511EPSS
SaveExploits0References2
NVD
NVD
•added 2026/08/06 2:16 a.m.•28 views

CVE-2026-18976

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

6.5CVSS0.00366EPSS
SaveExploits0References7
EUVD
EUVD
•added 2026/08/06 1:45 a.m.•22 views

EUVD-2026-53698

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

6.5CVSS6.2AI score0.00366EPSS
SaveExploits0References7
CVE
CVE
•added 2026/08/06 1:45 a.m.•142 views

CVE-2026-18976

The CVE affects NousResearch hermes-agent up to version 0.16.0. The vulnerability impacts the get_tool_definitions function in agent/agent_init.py within the disabled_toolsets Handler, where manipulation leads to incorrect privilege assignment. The issue could be exploited remotely and an exploit...

6.5CVSS6.2AI score0.00366EPSS
SaveExploits0References7
attackerkb
attackerkb
•added 2026/08/06 1:45 a.m.•24 views

CVE-2026-18976

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

6.5CVSS6.2AI score0.00366EPSS
SaveExploits0References7Affected Software1
Vulnrichment
Vulnrichment
•added 2026/08/06 1:45 a.m.•17 views

CVE-2026-18976 NousResearch hermes-agent disabled_toolsets agent_init.py get_tool_definitions privileges assignment

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

6.5CVSS6.2AI score0.00366EPSS
SaveExploits0References7
Cvelist
Cvelist
•added 2026/08/06 1:45 a.m.•55 views

CVE-2026-18976 NousResearch hermes-agent disabled_toolsets agent_init.py get_tool_definitions privileges assignment

A vulnerability was determined in NousResearch hermes-agent up to 0.16.0. This impacts the function gettooldefinitions of the file agent/agentinit.py of the component disabledtoolsets Handler. This manipulation causes incorrect privilege assignment. The attack may be initiated remotely. The explo...

6.5CVSS0.00366EPSS
SaveExploits0References7
Cvelist
Cvelist
•added 2026/08/05 10:54 p.m.•54 views

CVE-2026-67531 FrontMCP: CodeCall sandbox escape -> host RCE via live Zod schema exposure by getTool

FrontMCP is a TypeScript-first framework for the Model Context Protocol MCP. Prior to 1.5.7, the sandboxed codecall:execute tool exposes live host Zod schema instances to the script via getTool, and because Zod v4 defines zod as a non-configurable, non-writable own property, the ECMAScript Proxy...

9.3CVSS0.00735EPSS
SaveExploits0References2
BDU FSTEC
BDU FSTEC
•added 2026/05/25 12:00 a.m.•16 views

The vulnerability of the get_tool_by_id() function in the Open WebUI AI-based web interface allows a perpetrator to gain unauthorized access to protected information.

The vulnerability of the gettoolbyid function in the Open WebUI AI-based web interface is related to the lack of authorization when processing parameters like toolids and toolservers. Exploiting this vulnerability could allow a malicious actor to gain unauthorized access to protected information...

7.5CVSS5.8AI score0.00374EPSS
SaveExploits1References2Affected Software1
Rows per page
Query Builder