PT-2026-60301

Name of the Vulnerable Software and Affected Versions mcp versions prior to 1.28.1 Description The MCP Python SDK, a Python implementation of the Model Context Protocol, contains an issue in the deprecated mcp.server.websocket.websocket server transport. This component accepts WebSocket handshake...

GHSA-QW5R-PPCG-F8RJ MKP: Unbounded Pod Log Read via Attacker-Controlled `limitBytes`/`tailLines` Causes Memory Exhaustion

Unbounded Pod Log Read via Attacker-Controlled limitBytes/tailLines Causes Memory Exhaustion Summary The MKP Model Context Protocol for Kubernetes server exposes a getresource MCP tool that proxies Kubernetes pod log requests. User-supplied limitBytes and tailLines parameters are parsed as...

Security Bulletin: Langflow is affected by remote code execution, denial of service, path traversal, and exposed credentials due to multiple unauthenticated and insufficiently authorized API endpoints

Summary Langflow provides a visual interface for constructing and executing AI-powered agent workflows, exposing HTTP API endpoints for flow execution, file management, vector store operations, and Model Context Protocol MCP server configuration. An attacker could exploit insufficient validation...

PYSEC-2026-2918 PraisonAI Vulnerable to Sensitive Environment Variable Exposure via Untrusted MCP Subprocess Execution

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 default, the implementation forwards the entire parent proces...

PYSEC-2026-1617 Model Context Protocol (MCP) Python SDK does not enable DNS rebinding protection by default

Description The Model Context Protocol MCP Python SDK does not enable DNS rebinding protection by default for HTTP-based servers. When an HTTP-based MCP server is run on localhost without authentication using FastMCP with streamable HTTP or SSE transport, and has not configured...

CVE-2026-13341

A vulnerability exists in the Kong Konnect Model Context Protocol MCP server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests...

CVE-2026-13341 Prompt Injection and Credential Exposure via Untrusted Analytics Data in Kong Konnect MCP

A vulnerability exists in the Kong Konnect Model Context Protocol MCP server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests...

CVE-2026-13341

A vulnerability exists in the Kong Konnect Model Context Protocol MCP server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests...

EUVD-2026-41530

A vulnerability exists in the Kong Konnect Model Context Protocol MCP server prior to version 1.0.0, which could allow a remote attacker to perform an indirect prompt injection attack and execute unintended API requests...

PT-2026-55525

Name of the Vulnerable Software and Affected Versions Kong Konnect MCP server versions prior to 1.0.0 Description An issue exists where the server fails to properly validate content returned to the Large Language Model LLM. This allows a remote attacker to perform an indirect prompt injection by...

PYSEC-2026-472 PraisonAI MCP `tools/call` path-traversal => RCE via Python `.pth` injection

Summary PraisonAI's MCP Model Context Protocol server praisonai mcp serve registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joi...

EUVD-2026-37951

mcp-pinot: Unauthenticated tool invocation via default oauthenabled=False + host 0.0.0.0 bind...

GO-2026-5771 DNS Rebinding Protection Disabled by Default in Model Context Protocol Go SDK for Servers Running on Localhost in github.com/modelcontextprotocol/go-sdk

DNS Rebinding Protection Disabled by Default in Model Context Protocol Go SDK for Servers Running on Localhost in github.com/modelcontextprotocol/go-sdk...

PT-2026-50795

Name of the Vulnerable Software and Affected Versions mcp-pinot versions prior to 3.1.0 Description mcp-pinot is a Python-based Model Context Protocol MCP server for interacting with Apache Pinot. The software defaults to running an HTTP MCP server bound to 0.0.0.0:8080 without authentication. Th...

CVE-2026-11624

The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced...

CVE-2026-11624

The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced...

CVE-2026-11624

The CVE-2026-11624 entry concerns the Model Context Protocol server where origin validation of the Origin header affects DNS rebinding risk. Before v0.25.0 there was no host validation; v0.25.0 introduces --allowed-hosts and --allowed-origins flags to specify permitted hosts at startup. Both flag...

CVE-2026-11624

The Model Context Protocol has a security warning advising servers to validate the "Origin" header on all incoming connections to prevent DNS rebinding attacks. Prior to the v0.25.0 release, users had no way to validate the origin's host. In v0.25.0, a new "--allowed-hosts" flag was introduced...

PT-2026-49089

Name of the Vulnerable Software and Affected Versions Model Context Protocol versions prior to 0.25.0 Description Servers fail to validate the "Origin" header on incoming connections, which may allow DNS rebinding attacks. DNS rebinding is a method of bypassing the Same-Origin Policy to interact...

Agentjacking Attack Tricks AI Coding Agents Into Running Malicious Code

Cybersecurity researchers have described what they say is a new class of attack that can trick artificial intelligence AI coding agents into running arbitrary code on developer machines. Called Agentjacking by Tenet Security, the attack can be triggered by means of a fake error report crafted usi...