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...

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...

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...

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...

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...

Cross-site Request Forgery (CSRF)

Overview Affected versions of this package are vulnerable to Cross-site Request Forgery CSRF via the HTTP request handling process. An attacker can execute unauthorized actions by sending crafted cross-site POST requests with a CORS-safelisted Content-Type, bypassing origin and content-type...

MCP Servers Are the New Shadow IT for AI

Key Takeaways MCP servers are becoming the default wiring between AI agents and enterprise applications — but most organizations have zero visibility into where they are, what they expose, or how they can be abused. Qualys TotalAI now provides layered discovery of MCP servers across network, host...

AWS API MCP File Access Restriction Bypass

Description 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. Thi...

Improper Protection of Alternate Path

Overview awslabs.aws-api-mcp-server is a Model Context Protocol MCP server for interacting with AWS Affected versions of this package are vulnerable to Improper Protection of Alternate Path through the AWS CLI shorthand parser in awsapimcpserver/core/aws/services.py. An attacker can read arbitrar...

CVE-2026-31944

LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP Model Context Protocol OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redire...

CVE-2026-31944 LibreChat MCP OAuth callback does not validate browser session — allows token theft via redirect link

LibreChat is a ChatGPT clone with additional features. From 0.8.2 to 0.8.2-rc3, The MCP Model Context Protocol OAuth callback endpoint accepts the redirect from the identity provider and stores OAuth tokens for the user who initiated the flow, without verifying that the browser hitting the redire...

CVE-2026-31944

LibreChat’s breach involves the MCP OAuth callback endpoint incorrectly accepting redirects without verifying the user session or initiator. From versions 0.8.2 through 0.8.2-rc3, an attacker can lure a victim to complete the OAuth flow, causing the victim’s OAuth tokens to be stored on the attac...

CVE-2026-27825

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to version 0.17.0, the confluencedownloadattachment MCP tool accepts a downloadpath parameter that is written to without any directory boundary enforcement. An attacker who can call this tool an...

CVE-2026-27826

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to version 0.17.0, an unauthenticated attacker who can reach the mcp-atlassian HTTP endpoint can force the server process to make outbound HTTP requests to an arbitrary attacker-controlled URL b...

CVE-2026-27825 MCP Atlassian has an arbitrary file write leading to arbitrary code execution via unconstrained download_path in confluence_download_attachment

MCP Atlassian is a Model Context Protocol MCP server for Atlassian products Confluence and Jira. Prior to version 0.17.0, the confluencedownloadattachment MCP tool accepts a downloadpath parameter that is written to without any directory boundary enforcement. An attacker who can call this tool an...

GO-2026-4569 MCP Go SDK Vulnerable to Improper Handling of Case Sensitivity in github.com/modelcontextprotocol/go-sdk

MCP Go SDK Vulnerable to Improper Handling of Case Sensitivity in github.com/modelcontextprotocol/go-sdk...

MCP-In-SoS: Risk Assessment Framework for Open-Source MCP Servers

Model Context Protocol MCP servers have rapidly emerged over the past year as a widely adopted way to enable Large Language Model LLM agents to access dynamic, real-world tools. As MCP servers proliferate and become easy to adopt via open-source releases, understanding their security risks become...

Coverage-Guided Multi-Agent Harness Generation for Java Library Fuzzing

Coverage-guided fuzzing has proven effective for software testing, but targeting library code requires specialized fuzz harnesses that translate fuzzer-generated inputs into valid API invocations. Manual harness creation is time-consuming and requires deep understanding of API semantics,...

OpenClaw Vulnerable to Local File Exfiltration via MCP Tool Result MEDIA: Directive Injection

Summary A malicious or compromised MCP Model Context Protocol tool server can exfiltrate arbitrary local files from the host system by injecting MEDIA: directives into tool result text content. OpenClaw's tool result processing pipeline extracts file paths from MEDIA: tokens without source-level...

metasploit-mcp

metasploit-mcp Metasploit Framework MCP server for exploit ex...