PT-2026-43621

Name of the Vulnerable Software and Affected Versions python-engineio versions prior to 4.13.2 Description An attacker can trigger the creation of unnecessary background threads in the server by exploiting the heartbeat mechanism. This occurs when a new connection is received or when a client sen...

CVE-2026-44895

GitLab MCP Server lets an AI agent talk directly to GitLab. Prior to 0.6.0, the HTTP transport in src/transport.ts ships with no authentication layer at all and a wildcard Access-Control-Allow-Origin: on every response. The structural defect is that the SSE server stands up a stateful,...

EUVD-2026-32003

GitLab MCP Server lets an AI agent talk directly to GitLab. Prior to 0.6.0, the HTTP transport in src/transport.ts ships with no authentication layer at all and a wildcard Access-Control-Allow-Origin: on every response. The structural defect is that the SSE server stands up a stateful,...

CVE-2026-44895 GitLab MCP Server: SSE transport has no authentication and wildcard CORS, exposing all GitLab tools

GitLab MCP Server lets an AI agent talk directly to GitLab. Prior to 0.6.0, the HTTP transport in src/transport.ts ships with no authentication layer at all and a wildcard Access-Control-Allow-Origin: on every response. The structural defect is that the SSE server stands up a stateful,...

CVE-2026-44895 GitLab MCP Server: SSE transport has no authentication and wildcard CORS, exposing all GitLab tools

GitLab MCP Server lets an AI agent talk directly to GitLab. Prior to 0.6.0, the HTTP transport in src/transport.ts ships with no authentication layer at all and a wildcard Access-Control-Allow-Origin: on every response. The structural defect is that the SSE server stands up a stateful,...

CVE-2026-44895

CVE-2026-44895 (GitLab MCP Server SSE transport) has concrete technical details in the connected documents. The MCP server’s SSE HTTP transport (USE_SSE=true) ships with no authentication and sets Access-Control-Allow-Origin: * on all responses, exposing a stateful RPC endpoint backed by the oper...

Lumiverse 参数注入漏洞

Lumiverse is a full-featured AI chat application suite developed by Prolix OCs’ individual developers. Versions of Lumiverse prior to 0.9.7 contained a parameter injection vulnerability. This vulnerability stemmed from the MCP server creating endpoint validation commands without verifying the arg...

GitLab MCP Server 安全漏洞

GitLab MCP Server is an open-source tool developed by yoda.digital that connects AI agents with GitLab repositories. Versions of GitLab MCP Server prior to 0.6.0 contained security vulnerabilities. These vulnerabilities stemmed from the lack of authentication mechanisms at the HTTP transport laye...

PT-2026-43402

Lumiverse is a full-featured AI chat application. Prior to 0.9.7, the MCP server creation endpoint validates the command field against an allowlist of binary names but forwards the args array to the child process without any validation. Every binary on the allowlist accepts an inline-code executi...

PT-2026-43620

Name of the Vulnerable Software and Affected Versions radvd versions prior to 2.21 Description The radvdump utility contains a stack buffer overflow in the Route Information option parser. When processing a crafted ICMPv6 Router Advertisement, the print ff function copies up to 2032 bytes of...

Malicious code in explorhub-mcp-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9788bd481519def1387f4eccde46e4e6fbb3d8acc8e6b181397f299581d9a174 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2026-4312 Malicious code in explorhub-mcp-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 9788bd481519def1387f4eccde46e4e6fbb3d8acc8e6b181397f299581d9a174 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malicious Package

Overview explorhub-mcp-server is a malicious package. This package contains malicious code, and its content was removed from the official package manager. While this package might be attempting to impersonate a valid organization, there is no connection between that organization and this package...

MAL-2026-4774 Malicious code in vulndify-mcp-server (PyPI)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 6110bfbfb3eac275094aefd342ef273350829f83c53c480e29df1f872b335650 The package advertises itself in the README as offering only a benign hello MCP tool, but src/vulndifymcpserver/server.py registers two additional,...

Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret | Field | Value | | ---------------- | ----- | | Repository | Jovancoding/Network-AI | | Affected version | v5.4.4 commit c12686e181f231cf8d7bcf836a96d78f0f0877ac | Summary The MCP SSE server defaults to an empty secret...

@toolsdk.ai/registry (=1.0.83), easy-mcp-server (>=1.0.117 <=1.0.118) potentially affected by CVE-2026-46519 via mcp-server-kubernetes (>=2.4.3 <=2.9.9)

mcp-server-kubernetes NPM version =2.4.3, =1.0.117, =1.0.118 Source cves: CVE-2026-46519 Source advisory: OSV:GHSA-CR22-WJX7-2W6M...

Incorrect Authorization

Overview mcp-server-kubernetes is a MCP server for interacting with Kubernetes clusters via kubectl Affected versions of this package are vulnerable to Incorrect Authorization through the CallTool handler in src/index.ts. An attacker can invoke disallowed Kubernetes tools and perform destructive...

GHSA-CR22-WJX7-2W6M MCP Server Kubernetes: Tool Access Control Bypass via Presentation-Layer Filtering Without Execution-Layer Enforcement

Summary mcp-server-kubernetes exposes three environment variables ALLOWONLYREADONLYTOOLS, ALLOWONLYNONDESTRUCTIVETOOLS, ALLOWEDTOOLS documented as access controls for restricting which Kubernetes operations are available. These controls are enforced at the tool discovery layer tools/list but not ...

MCP Server Kubernetes: Tool Access Control Bypass via Presentation-Layer Filtering Without Execution-Layer Enforcement

Summary mcp-server-kubernetes exposes three environment variables ALLOWONLYREADONLYTOOLS, ALLOWONLYNONDESTRUCTIVETOOLS, ALLOWEDTOOLS documented as access controls for restricting which Kubernetes operations are available. These controls are enforced at the tool discovery layer tools/list but not ...

PT-2026-42619

Summary mcp-server-kubernetes exposes three environment variables ALLOW ONLY READONLY TOOLS, ALLOW ONLY NON DESTRUCTIVE TOOLS, ALLOWED TOOLS documented as access controls for restricting which Kubernetes operations are available. These controls are enforced at the tool discovery layer tools/list...