Langflow 安全漏洞

Langflow is an open-source visualization framework developed by Langflow for building multi-agent and RAG applications. Versions of Langflow 1.8.3 and earlier contain security vulnerabilities. These vulnerabilities stem from incorrect operations on the function getclientip/installmcpconfig in the...

Apache Doris MCP Server 安全漏洞

Apache Doris MCP Server is a context-based protocol backend service provided by the Apache Foundation. Versions of Apache Doris MCP Server prior to 0.6.1 contained security vulnerabilities. These vulnerabilities stemmed from improper handling of query contexts, which could lead to the execution o...

PT-2026-33705

Name of the Vulnerable Software and Affected Versions langflow-ai langflow versions prior to 1.8.4 Description An issue exists in the Model Context Protocol Configuration API within the get client ip/install mcp config functions of the file src/backend/base/langflow/api/v1/mcp projects.py. A remo...

PT-2026-33643

Name of the Vulnerable Software and Affected Versions Apache Doris MCP Server versions prior to 0.6.1 Description An improper neutralization flaw in query context handling within the MCP query execution interface may allow the execution of unintended SQL statements. This can lead to the bypass of...

Command Injection

Overview PraisonAI is a PraisonAI is an AI Agents Framework with Self Reflection. PraisonAI application combines PraisonAI Agents, AutoGen, and CrewAI into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent...

PraisonAI has an incomplete fix for CVE-2026-34935 - OS Command Injection

Summary The fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand, allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. Affected Package - Ecosystem: PyP...

GHSA-9QHQ-V63V-FV3J PraisonAI has an incomplete fix for CVE-2026-34935 - OS Command Injection

Summary The fix for PraisonAI's MCP command handling does not add a command allowlist or argument validation to parsemcpcommand, allowing arbitrary executables like bash, python, or /bin/sh with inline code execution flags to pass through to subprocess execution. Affected Package - Ecosystem: PyP...

Insufficient Granularity of Access Control

Overview mcp-neo4j-cypher is an A simple Neo4j MCP server Affected versions of this package are vulnerable to Insufficient Granularity of Access Control in the readonly mode in CALL procedures. An attacker can perform unauthorized actions and potentially access internal resources by bypassing...

Neo4j Labs MCP Servers: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures

Summary The readonly mode in mcp-neo4j-cypher versions prior to 0.6.0 can be bypassed using CALL procedures. Details Impact The enforcing of readonly mode in vulnerable versions could be bypassed by certain APOC procedures. Patches v0.6.0 release hardened the checks around the mode. The only way ...

EUVD-2026-23518

Neo4j Labs MCP Servers: SSRF and Data Modification via readonly Mode Bypass Through CALL Procedures...

CVE-2026-35402

mcp-neo4j-cypher is an MCP server for executing Cypher queries against Neo4j databases. In versions prior to 0.6.0, the readonly mode enforcement can be bypassed using APOC CALL procedures, potentially allowing unauthorized write operations or server-side request forgery. This issue is fixed in...

CVE-2026-35402

mcp-neo4j-cypher is an MCP server for executing Cypher queries against Neo4j databases. In versions prior to 0.6.0, the readonly mode enforcement can be bypassed using APOC CALL procedures, potentially allowing unauthorized write operations or server-side request forgery. This issue is fixed in...

CVE-2026-35402 mcp-neo4j-cypher: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures

mcp-neo4j-cypher is an MCP server for executing Cypher queries against Neo4j databases. In versions prior to 0.6.0, the readonly mode enforcement can be bypassed using APOC CALL procedures, potentially allowing unauthorized write operations or server-side request forgery. This issue is fixed in...

CVE-2026-35402 mcp-neo4j-cypher: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures

mcp-neo4j-cypher is an MCP server for executing Cypher queries against Neo4j databases. In versions prior to 0.6.0, the readonly mode enforcement can be bypassed using APOC CALL procedures, potentially allowing unauthorized write operations or server-side request forgery. This issue is fixed in...

EUVD-2026-23400

A flaw was found in the AAP MCP server. An unauthenticated remote attacker can exploit a log injection vulnerability by sending specially crafted input to the toolsetroute parameter. This parameter is not properly sanitized before being written to logs, allowing the attacker to inject control...

CVE-2026-6494

CVE-2026-6494 describes a log-injection vulnerability in the AAP MCP server. An unauthenticated remote attacker can send specially crafted input to the toolsetroute parameter, which is written to logs without proper sanitization. This allows insertion of control characters (e.g., newlines and ANS...

PT-2026-37122

Name of the Vulnerable Software and Affected Versions PraisonAI versions prior to 4.6.9 Description Insufficient command handling in the parse mcp command function allows for arbitrary code execution. The function fails to implement a command allowlist or argument validation, enabling executables...

CVE-2026-39313

mcp-framework is a framework for building Model Context Protocol MCP servers. In versions 0.2.21 and below, the readRequestBody function in the HTTP transport concatenates request body chunks into a string with no size limit. Although a maxMessageSize configuration value exists, it is never...

Partial String Comparison

Overview flowise-components is a Flowiseai Components Affected versions of this package are vulnerable to Partial String Comparison due to the replaceInputsWithConfig logic in packages/server/src/utils/index.ts. An attacker can override flow parameters by supplying a crafted override configuratio...

CVE-2026-39313 MCP-Framework: Unbounded memory allocation in readRequestBody allows denial of service via HTTP transport

mcp-framework is a framework for building Model Context Protocol MCP servers. In versions 0.2.21 and below, the readRequestBody function in the HTTP transport concatenates request body chunks into a string with no size limit. Although a maxMessageSize configuration value exists, it is never...