Lucene search
+L

129 matches found

Kitploit
Kitploit
•added 2026/11/18 11:56 p.m.•34 views

inspector

MCP Inspector A developer tool for inspecting Model Context Protocol MCP servers. It ships as a single package, @modelcontextprotocol/inspector, that provides four ways to inspect a server: Web — a Vite + React + Mantine single-page app with a Node backend. CLI — a scriptable command-line client...

6.4AI score
SaveExploits0References10
Kitploit
Kitploit
•added 2026/11/17 9:14 p.m.•28 views

Ajar

Ajar: Measuring Open Privilege in Agent Defenses An agent-security benchmark reports two numbers, attack success and benign utility, and both are read off runs that happened. Neither says what the defense stood ready to allow on the paths no run took. Ajar asks it directly: for each benign task i...

6.3AI score
SaveExploits0References1
Packet Storm News
Packet Storm News
•added 2026/11/08 12:00 a.m.•7 views

Least-Privilege Auditing of Agent Tool Calls with Intent Graphs and Reasoning-Guided Escalation

LLM agents that call tools are exposed to indirect prompt injection: instructions hidden in tool outputs can steer an agent into calls the user never asked for. We present a runtime audit that derives an executable intent graph from the user's objective and the deployment's tool catalog with one...

6AI score
SaveExploits0
NVD
NVD
•added 2026/11/06 8:17 p.m.•23 views

CVE-2026-124028

mistral.rs before 0.9.5 contains a delimiter injection vulnerability in mistralrs-core that allows attackers to inject tool calls by placing delimiter strings in text the model quotes. Attackers controlling documents, web pages or tool outputs can embed tags like to make qwen-xml, gemma4 or...

4.2CVSS0.00189EPSS
SaveExploits0References6
CVE
CVE
•added 2026/11/06 7:14 p.m.•20 views

CVE-2026-124028

Versions of mistral.rs before 0.9.5 are affected by a delimiter injection vulnerability in the mistralrs-core component. This flaw occurs because the software fails to properly neutralize delimiter strings within text quoted by the model. An attacker who controls external inputs—such as documents...

4.2CVSS5.9AI score0.00189EPSS
SaveExploits0References6
EUVD
EUVD
•added 2026/11/06 7:14 p.m.•12 views

EUVD-2026-118436

mistral.rs before 0.9.5 contains a delimiter injection vulnerability in mistralrs-core that allows attackers to inject tool calls by placing delimiter strings in text the model quotes. Attackers controlling documents, web pages or tool outputs can embed tags like to make qwen-xml, gemma4 or...

4.2CVSS5.9AI score0.00189EPSS
SaveExploits0References6
NVD
NVD
•added 2026/10/30 9:17 p.m.•17 views

CVE-2026-62863

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...

9.6CVSS0.00314EPSS
SaveExploits0References4
CVE
CVE
•added 2026/10/30 8:33 p.m.•27 views

CVE-2026-62863

The MoLing MCP server (prior to version 0.5.0 ) is vulnerable to unauthorized tool execution due to unauthenticated SSE and wildcard CORS settings. When running in SSE mode using the -l flag, the /sse and /message endpoints fail to authenticate requests, and the mcp-go dependency sets Access-Cont...

9.6CVSS6AI score0.00314EPSS
SaveExploits0References4
EUVD
EUVD
•added 2026/10/30 8:33 p.m.•19 views

EUVD-2026-114460

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...

9.6CVSS6AI score0.00314EPSS
SaveExploits0References4
Cvelist
Cvelist
•added 2026/10/30 8:33 p.m.•39 views

CVE-2026-62863 MoLing: unauthenticated SSE and wildcard CORS expose tool sessions

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...

9.6CVSS0.00314EPSS
SaveExploits0References4
osv_cve
osv_cve
•added 2026/10/30 8:33 p.m.•29 views

CVE-2026-62863 MoLing: unauthenticated SSE and wildcard CORS expose tool sessions

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...

9.6CVSS6AI score0.00314EPSS
SaveExploits0References6
Mend
Mend
•added 2026/10/30 8:33 p.m.•13 views

CVE-2026-62863

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using "-l", its "/sse" and "/message" HTTP endpoints do not authenticate requests and the "mcp-go" dependency sets "Access-Control-Allow-Origin: ". A malicious web page can open a cross-origin...

9.6CVSS6AI score0.00314EPSS
SaveExploits0References6
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2026/10/30 12:00 a.m.•16 views

CVE-2026-62863: gojue moling: MoLing is a computer-use and browser-use based MCP server

MoLing is a computer-use and browser-use based MCP server. Prior to 0.5.0, when MoLing runs in SSE mode using -l, its /sse and /message HTTP endpoints do not authenticate requests and the mcp-go dependency sets Access-Control-Allow-Origin: . A malicious web page can open a cross-origin EventSourc...

9.6CVSS6AI score0.00314EPSS
SaveExploits0References3
Positive Technologies
Positive Technologies
•added 2026/10/30 12:00 a.m.•18 views

PT-2026-134207

Name of the Vulnerable Software and Affected Versions MoLing versions prior to 0.5.0 Description When running in SSE mode using the -l flag, the /sse and /message HTTP endpoints do not authenticate requests. Additionally, the mcp-go dependency configures Access-Control-Allow-Origin: , which allow...

9.6CVSS5.9AI score0.00314EPSS
SaveExploits0References10
Spring Security Advisories
Spring Security Advisories
•added 2026/10/28 12:00 a.m.•16 views

Spring AI 2.1 Message Parts: Reasoning That Survives the Round Trip

Spring AI: Message Parts Doc | Upgrade Notes | OpenAI Responses Doc | Session Doc Reasoning models do more than think before they answer. They hand part of that thinking back to you and expect to get it back on the next request. Claude signs its thinking blocks. Gemini attaches thought signatures...

6.4AI score
SaveExploits0
EUVD
EUVD
•added 2026/10/27 7:29 p.m.•21 views

EUVD-2026-111366

The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...

6.5CVSS5.9AI score0.00337EPSS
SaveExploits0References7
osv_cve
osv_cve
•added 2026/10/27 7:29 p.m.•26 views

CVE-2026-116686 Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas

The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...

6.5CVSS5.8AI score
SaveExploits0References9
Vulnrichment
Vulnrichment
•added 2026/10/27 7:29 p.m.•15 views

CVE-2026-116686 Model Context Protocol Python SDK: Client fetched server-chosen $ref URLs while validating tool results against output schemas

The Model Context Protocol Python SDK is the official Python SDK for Model Context Protocol servers and clients. From 1.10.0 until 1.30.0 and 2.2.0, ClientSession, ClientSessionGroup, and Client tool calls validate server-declared outputSchema documents with jsonschema's default resolver, causing...

6.5CVSS5.9AI score0.00337EPSS
SaveExploits0References7
NVD
NVD
•added 2026/10/23 3:17 p.m.•19 views

CVE-2026-58497

Uni-CLI gives people and agents one command interface for websites, browsers, desktop applications, local tools, and MCP. Prior to version 0.225.2, Uni-CLI exposed the legacy JSON-RPC-over-HTTP MCP transport on loopback without validating browser Origin headers before routing requests. A maliciou...

8.6CVSS0.00255EPSS
SaveExploits0References2
Mend
Mend
•added 2026/10/23 2:49 p.m.•9 views

CVE-2026-58497

Uni-CLI gives people and agents one command interface for websites, browsers, desktop applications, local tools, and MCP. Prior to version 0.225.2, Uni-CLI exposed the legacy JSON-RPC-over-HTTP MCP transport on loopback without validating browser Origin headers before routing requests. A maliciou...

8.6CVSS5.7AI score0.00255EPSS
SaveExploits0References5
Rows per page
Query Builder