CVE-2025-68144: Improper Neutralization of Argument Delimiters in a Command

In mcp-server-git versions prior to 2025.12.17, the gitdiff and gitcheckout functions passed user-controlled arguments directly to git CLI commands without sanitization. Flag-like values e.g., --output=/path/to/file for gitdiff would be interpreted as command-line options rather than git refs,...

CVE-2025-68145: Improper Limitation of a Pathname to a Restricted Directory

In mcp-server-git versions prior to 2025.12.17, when the server is started with the --repository flag to restrict operations to a specific repository path, it did not validate that repopath arguments in subsequent tool calls were actually within that configured path. This could allow tool calls t...

Malicious code in vscode-azure-mcp-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ee81b2442f4cf9659439b86f4d75212f59a5471403e97b4720448df2997d1561 The package vscode-azure-mcp-server was found to contain malicious code. Source: ghsa-malware...

MAL-2025-192601 Malicious code in vscode-azure-mcp-server (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector ee81b2442f4cf9659439b86f4d75212f59a5471403e97b4720448df2997d1561 The package vscode-azure-mcp-server was found to contain malicious code. Source: ghsa-malware...

EUVD-2025-203811

Malicious code in vscode-azure-mcp-server npm...

Arbitrary Command Injection

mcp-server-kubernetes is vulnerable to Arbitrary Command Injection. The vulnerability is due to passing user-supplied command strings directly to shell execution sh -c without input validation, which allows an attacker to inject and execute arbitrary commands through crafted inputs or indirect...

Missing Authorization

Jenkins MCP Server Plugin is vulnerable to Missing Authorization. The vulnerability is due to missing permission checks in multiple MCP tools, which allows an attacker to trigger builds and access sensitive information related to job and cloud configurations without proper authorization...

Important: Red Hat Security Advisory: Red Hat Ansible Automation Platform 2.6 Container Release Update

An update is now available for Red Hat Ansible Automation Platform 2.6 Red Hat Ansible Automation Platform provides an enterprise framework for building, deploying and managing IT automation at scale. IT Managers can provide top-down guidelines on how automation is applied to individual teams,...

Fetch MCP Server has a Server-Side Request Forgery (SSRF) vulnerability

fetch-mcp v1.0.2 and before is vulnerable to Server-Side Request Forgery SSRF vulnerability, which allows attackers to bypass private IP validation and access internal network resources...

GHSA-8FXJ-2G9Q-8FJW Fetch MCP Server has a Server-Side Request Forgery (SSRF) vulnerability

fetch-mcp v1.0.2 and before is vulnerable to Server-Side Request Forgery SSRF vulnerability, which allows attackers to bypass private IP validation and access internal network resources...

Markdownify MCP Server 安全漏洞

Markdownify MCP Server is a Model Context Protocol server for converting almost any content to Markdown by Zach Caceres, an individual developer in the United States. A security vulnerability exists in Markdownify MCP Server version 0.0.2 and earlier, which stems from a server-side request forger...

Server-side Request Forgery (SSRF)

Overview mcp-fetch-server is an An MCP server offering simple HTTP fetch functionality Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the fetch method, in the isipprivate function. An attacker can access internal network resources by sending crafted...

Exploit for Deserialization of Untrusted Data in Siemens 6Bk1602-0Aa12-0Tp0_Firmware

MCP Exploit-DB Server An MCP Model Context Protocol server...

CVE-2025-66404

MCP Server Kubernetes is an MCP Server that can connect to a Kubernetes cluster and manage it. Prior to 2.9.8, there is a security issue exists in the execinpod tool of the mcp-server-kubernetes MCP Server. The tool accepts user-provided commands in both array and string formats. When a string...

Arbitrary Command Injection

Overview mcp-server-kubernetes is a MCP server for interacting with Kubernetes clusters via kubectl Affected versions of this package are vulnerable to Arbitrary Command Injection via the execinpod tool. An attacker can execute arbitrary commands within Kubernetes pods by supplying crafted input...

mcp-server-kubernetes has potential security issue in exec_in_pod tool

Summary A security issue exists in the execinpod tool of the mcp-server-kubernetes MCP Server. The tool accepts user-provided commands in both array and string formats. When a string format is provided, it is passed directly to shell interpretation sh -c without input validation, allowing shell...

GHSA-WVXP-JP4W-W8WG mcp-server-kubernetes has potential security issue in exec_in_pod tool

Summary A security issue exists in the execinpod tool of the mcp-server-kubernetes MCP Server. The tool accepts user-provided commands in both array and string formats. When a string format is provided, it is passed directly to shell interpretation sh -c without input validation, allowing shell...

@toolsdk.ai/registry (1.0.83) potentially affected by CVE-2025-66404 via mcp-server-kubernetes (2.4.3)

mcp-server-kubernetes NPM version 2.4.3 is affected by a known vulnerability. The following packages have a transitive dependency on mcp-server-kubernetes and may be impacted: - @toolsdk.ai/registry 1.0.83 Source cves: CVE-2025-66404 Source advisory: SNYK:JS-MCPSERVERKUBERNETES-14176095...

@toolsdk.ai/registry (1.0.83) potentially affected by CVE-2025-66404 via mcp-server-kubernetes (2.4.3)

mcp-server-kubernetes NPM version 2.4.3 is affected by a known vulnerability. The following packages have a transitive dependency on mcp-server-kubernetes and may be impacted: - @toolsdk.ai/registry 1.0.83 Source cves: CVE-2025-66404 Source advisory: OSV:GHSA-WVXP-JP4W-W8WG...

CVE-2025-66404

The CVE-2025-66404 entry concerns mcp-server-kubernetes. The exec_in_pod tool accepts a string command and passes it to a shell (sh -c) without input validation, enabling shell metacharacters to be interpreted. This creates potential for direct command injection or indirect prompt injection, allo...