CVE-2026-67430

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not expire sessions by default, so repeated initialize requests retain unbounded ServerSession objects and can exhaust proces...

CVE-2026-63118 MCP Ruby SDK: Streamable HTTP transport lacks DNS-rebinding (Host/Origin) protection

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not validate the HTTP Host or Origin request headers, which allows a malicious browser page to use DNS rebinding to reach a...

CVE-2026-63118 MCP Ruby SDK: Streamable HTTP transport lacks DNS-rebinding (Host/Origin) protection

MCP Ruby SDK is the official Ruby SDK for Model Context Protocol servers and clients. Prior to 0.23.0, MCP::Server::Transports::StreamableHTTPTransport in the mcp gem does not validate the HTTP Host or Origin request headers, which allows a malicious browser page to use DNS rebinding to reach a...

PT-2026-65899

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem reads and parses an entire JSON-RPC POST body without enforcing a size limit. This allows an unauthenticated remote attacker...

PT-2026-65888

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem fails to validate the HTTP Host or Origin request headers. This allows a malicious browser page to utilize DNS rebinding—a...

PT-2026-65898

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem fails to bind a session ID to a session owner. This allows an attacker who has obtained a stolen session ID to send tools/ca...

PT-2026-65897

Name of the Vulnerable Software and Affected Versions mcp versions prior to 0.23.0 Description The MCP::Server::Transports::StreamableHTTPTransport component in the mcp gem does not expire sessions by default. Consequently, repeated initialize requests lead to the retention of unbounded...

The risk hiding behind exposed MCP servers

How unauthenticated Model Context Protocol MCP servers are opening doors to sensitive cloud data, IAM, and command execution...

pentest-confirm-mcp

pentest-confirm-mcp Model Context Protocol MCP server for...

Exploit for CVE-2026-66012

CVE-2026-66012 — SiYuan MCP Unauthenticated Administrator Take...

GHSA-29W2-FQ35-V728 AWS API MCP Server Security Policy Bypass via Startup Initialization Failure

Summary The AWS API MCP Server is an open source Model Context Protocol MCP server that enables AI assistants to interact with AWS services and resources through AWS CLI commands. It provides programmatic access to manage your AWS infrastructure while maintaining proper security controls. It...

CVE-2026-44192

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

EUVD-2026-47652

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

CVE-2026-44192

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

CVE-2026-44192 Ansible-lightspeed: ansible lightspeed mcp server: remote code execution and data exfiltration via path traversal

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

CVE-2026-44192: Improper Limitation of a Pathname to a Restricted Directory

A flaw was found in the Ansible Lightspeed Model Context Protocol MCP server. This vulnerability, known as path traversal, allows an attacker to manipulate an AI agent through indirect prompt injection. By doing so, the attacker can cause the server to write files to unauthorized locations on the...

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395 PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model context

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, PraisonAI's direct-prompt CLI automatically expands @url: mentions in raw prompt text before agent execution begins. If a prompt contains @url:, the CLI calls...

CVE-2026-47395

CVE-2026-47395 – PraisonAI CLI loopback/SSRF via @url: mentions Prior to PraisonAI v4.6.40 (and praisonaiagents v1.6.40), the direct-prompt CLI automatically expands @url:(http|https) prompts, performing an unrestricted urllib.request.urlopen() to the attacker-controlled URL. The fetched response...