EUVD-2026-16769

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP Model Context Protocol servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containin...

CVE-2026-31951

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP Model Context Protocol servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containin...

CVE-2026-31951 LibreChat's MCP Server Header Injection Enables OAuth Token Theft

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP Model Context Protocol servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containin...

CVE-2026-31951

Vulnerability summary : LibreChat’s MCP server feature (versions 0.8.2-rc1 to 0.8.3-rc1) allows arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can host a malicious MCP server with headers like {{LIBRECHAT_OPENID_ACCESS_TOKEN}} to exfiltrate victims’ OAuth tok...

CVE-2026-31951 LibreChat's MCP Server Header Injection Enables OAuth Token Theft

LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP Model Context Protocol servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containin...

PT-2026-28582

Name of the Vulnerable Software and Affected Versions Azure Data Explorer MCP Server versions prior to commit 0abe0ee55279e111281076393e5e966335fffd30 Azure Data Explorer MCP Server versions up to and including 0.1.1 Description Azure Data Explorer MCP Server, a Model Context Protocol MCP server,...

PT-2026-28432

Name of the Vulnerable Software and Affected Versions LibreChat versions 0.8.2-rc1 through 0.8.3-rc1 Description LibreChat, a ChatGPT clone, has an issue where user-created Model Context Protocol MCP servers can include arbitrary HTTP headers. These headers are subject to credential placeholder...

PT-2026-28576

Name of the Vulnerable Software and Affected Versions MCP Ruby SDK versions prior to 0.9.2 Description The Ruby SDK for Model Context Protocol servers and clients contains a session hijacking issue in its streamable http transport.rb implementation. An attacker obtaining a valid session ID can...

MCP Ruby SDK 安全漏洞

MCP Ruby SDK is an open-source development toolkit for building and interacting with Model Context Protocol clients. Versions of the MCP Ruby SDK prior to 0.9.2 contained security vulnerabilities. These vulnerabilities stemmed from issues with the streamablehttptransport.rb implementation, which...

CVE-2026-23882

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

CVE-2026-23882

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

CVE-2026-23882 Blinko: Admin RCE - MCP Server Command Injection

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

EUVD-2026-14545

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

CVE-2026-23882 Blinko: Admin RCE - MCP Server Command Injection

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

GO-2026-4773 Cross-Site Tool Execution for HTTP Servers without Authorizatrion in github.com/modelcontextprotocol/go-sdk

Cross-Site Tool Execution for HTTP Servers without Authorizatrion in github.com/modelcontextprotocol/go-sdk...

PT-2026-27217

Blinko is an AI-powered card note-taking project. Prior to version 1.8.4, the MCP Model Context Protocol server creation function allows specifying arbitrary commands and arguments, which are executed when testing the connection. This issue has been patched in version 1.8.4...

MCP Go SDK 跨站请求伪造漏洞

MCP Go SDK is an open-source development toolkit for the Model Context Protocol. Versions of MCP Go SDK prior to 1.4.1 contained a cross-site request forgeing vulnerability. This vulnerability stemmed from Streamable HTTP transmissions that did not validate the Origin header and did not specify t...

STRIATUM-CTF: A Protocol-Driven Agentic Framework for General-Purpose CTF Solving

Large Language Models LLMs have demonstrated potential in code generation, yet they struggle with the multi-step, stateful reasoning required for offensive cybersecurity operations. Existing research often relies on static benchmarks that fail to capture the dynamic nature of real-world...

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol MCP has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client...

T-MAP: Red-Teaming LLM Agents with Trajectory-Aware Evolutionary Search

While prior red-teaming efforts have focused on eliciting harmful text outputs from large language models LLMs, such approaches fail to capture agent-specific vulnerabilities that emerge through multi-step tool execution, particularly in rapidly growing ecosystems such as the Model Context Protoc...