428 matches found
Command Injection
Overview aws-mcp is an AWS Model Context Protocol Server Affected versions of this package are vulnerable to Command Injection via improper validation of user-supplied input in the allowed commands process. An attacker can execute arbitrary system commands by supplying crafted input that is used ...
aws-mcp-server 操作系统命令注入漏洞
aws-mcp-server is a lightweight service developed by Alexei Ledenev. It enables AI assistants to execute AWS CLI commands through the Model Context Protocol MCP in a secure, containerized environment. aws-mcp-server has an operating system command injection vulnerability, which stems from...
aws-mcp-server 操作系统命令注入漏洞
aws-mcp-server is a lightweight service developed by Alexei Ledenev. It enables AI assistants to execute AWS CLI commands through the Model Context Protocol MCP in a secure, containerized environment. aws-mcp-server has an operating system command injection vulnerability, which stems from...
Missing Authentication for Critical Function
Overview n8n-mcp is an Integration between n8n workflow automation and Model Context Protocol MCP Affected versions of this package are vulnerable to Missing Authentication for Critical Function due to missing authentication in several HTTP transport endpoints and exposure of sensitive operationa...
CVE-2026-40159
PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By...
CVE-2026-40159 PraisonAI Exposes Sensitive Environment Variable via Untrusted MCP Subprocess Execution
PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By...
CVE-2026-40159
PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By...
CVE-2026-40159 PraisonAI Exposes Sensitive Environment Variable via Untrusted MCP Subprocess Execution
PraisonAI is a multi-agent teams system. Prior to 4.5.128, PraisonAI’s MCP Model Context Protocol integration allows spawning background servers via stdio using user-supplied command strings e.g., MCP"npx -y @smithery/cli ...". These commands are executed through Python’s subprocess module. By...
CVE-2026-40159
PraisonAI's MCP integration (before 4.5.128) spawns background processes via stdio using user-supplied commands, and forwards the full parent environment to the subprocess. This allows any MCP invocation to inherit sensitive variables (API keys, tokens, database credentials), enabling potential c...
CVE-2026-35577 Missing Host Header Validation in Apollo MCP Server for Localhost Deployments
Apollo MCP Server is a Model Context Protocol server that exposes GraphQL operations as MCP tools. Prior to version 1.7.0, the Apollo MCP Server did not validate the Host header on incoming HTTP requests when using StreamableHTTP transport. In configurations where an HTTP-based MCP server is run ...
EUVD-2026-20968
n8n-MCP is a Model Context Protocol MCP server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTHTOKEN to cause the server to iss...
CVE-2026-39974
n8n-MCP is a Model Context Protocol MCP server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTHTOKEN to cause the server to iss...
CVE-2026-39974 n8n-MCP has an Authenticated SSRF via instance-URL header in multi-tenant HTTP mode
n8n-MCP is a Model Context Protocol MCP server that provides AI assistants with comprehensive access to n8n node documentation, properties, and operations. Prior to 2.47.4, an authenticated Server-Side Request Forgery in n8n-mcp allows a caller holding a valid AUTHTOKEN to cause the server to iss...
PT-2026-31715
Apollo MCP Server is a Model Context Protocol server that exposes GraphQL operations as MCP tools. Prior to version 1.7.0, the Apollo MCP Server did not validate the Host header on incoming HTTP requests when using StreamableHTTP transport. In configurations where an HTTP-based MCP server is run ...
Arbitrary Command Injection
Overview @idachev/mcp-javadc is a Model Context Protocol MCP server for Java decompilation Affected versions of this package are vulnerable to Arbitrary Command Injection via the HTTP Interface component when processing the jarFilePath argument. An attacker can execute arbitrary operating system...
PT-2026-31451
FrontMCP is a TypeScript-first framework for the Model Context Protocol MCP. Prior to 2.3.0, the mcp-from-openapi library uses @apidevtools/json-schema-ref-parser to dereference $ref pointers in OpenAPI specifications without configuring any URL restrictions or custom resolvers. A malicious OpenA...
MCP-DPT: A Defense-Placement Taxonomy and Coverage Analysis for Model Context Protocol Security
The Model Context Protocol MCP enables large language models LLMs to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only interactions, MCP exposes pre-execution artifacts, shared context,...
CVE-2026-35568
MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to 1.0.0, the java-sdk contains a DNS rebinding vulnerability. This vulnerability allows an attacker to access a locally or network-private java-sdk MCP server via a victims browser that is either local, o...
CVE-2026-35568
The CVE-2026-35568 entry corresponds to a DNS rebinding vulnerability in the MCP Java SDK (official Java SDK for Model Context Protocol servers/clients). Prior to version 1.0.0, the java-sdk did not validate the Origin header, enabling an attacker-controlled webpage on local or adjacent networks ...
CVE-2026-35568 MCP Java-SDK has a DNS Rebinding Vulnerability
MCP Java SDK is the official Java SDK for Model Context Protocol servers and clients. Prior to 1.0.0, the java-sdk contains a DNS rebinding vulnerability. This vulnerability allows an attacker to access a locally or network-private java-sdk MCP server via a victims browser that is either local, o...