Updating the taxonomy of failure modes in agentic AI systems: What a year of red teaming taught us

In this article 1. Why the Taxonomy Needed Updating 2. Seven new failure modes 3. Operational findings: What red teaming showed 4. New mitigations 5. What to do this quarter When the Microsoft AI Red Team published the Taxonomy of Failure Modes in Agentic AI Systems in April 2025, the goal was a...

ROOT-APP-NPM-CVE-2025-49596 CVE-2025-49596 in @rootio/modelcontextprotocol__inspector - Patched by Root

Root has patched CVE-2025-49596 in the @rootio/modelcontextprotocolinspector package for Root:npm. Multiple fixed versions available...

cybersec-mcp

🛡️ Cybersecurity Professor MCP Server Prof. Null — Tu pro...

CVE-2026-32625

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol MCP server integration resolves $VAR placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any...

CVE-2026-45609

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol MCP security specifications. Specifically, it processes untrusted...

PT-2026-45878

Name of the Vulnerable Software and Affected Versions LibreChat versions prior to 0.8.4-rc1 Description LibreChat is an enhanced ChatGPT clone supporting multiple AI providers. The Model Context Protocol MCP server integration improperly resolves $VAR placeholders against the server's process.env...

Jenkins Server MCP 代码问题漏洞

Jenkins Server MCP is a model context protocol server developed by Hekmon for individual developers to interact with Jenkins CI/CD servers. Version 0.1.0 of Jenkins Server MCP contains code vulnerabilities. These vulnerabilities stem from incorrect operations in the functions jobPath of the files...

AEM MCP Server 代码问题漏洞

The AEM MCP Server is a model context protocol server developed by Indrasishbanerjee, designed for content, components, and asset management. The AEM MCP Server has a code vulnerability that stems from incorrect handling of the parameter assetPath in the getAssetMetadata function within the Axios...

CVE-2026-45609

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol MCP security specifications. Specifically, it processes untrusted...

CVE-2026-45609 mcp-security: Unvalidated URL Fetching (SSRF)

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol MCP security specifications. Specifically, it processes untrusted...

EUVD-2026-33323

mcp-security provides Security and Authorization support for Model Context Protocol in Spring AI. Prior to 0.1.9, the mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol MCP security specifications. Specifically, it processes untrusted...

n8n-MCP 安全漏洞

n8n-MCP is a model context protocol server developed by Romuald Członkowski, an individual developer. Versions of n8n-MCP prior to 2.51.3 contained security vulnerabilities. These vulnerabilities stemmed from the fact that the workflow telemetry cleaner might retain fragments of URL shape node...

Exploit for OS Command Injection in Arcane

CVE-2026-23520: Model Context Protocol MCP Connect RCE - Edu...

Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

The Model Context Protocol MCP standardizes how a large-language-model LLM agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a...

A First Measurement Study on Authentication Security in Real-World Remote MCP Servers

The Model Context Protocol MCP is emerging as a common interface connecting large language models LLMs with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such...

VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers

Model Context Protocol MCP has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to agent-driven invocation, implementation flaws in tool handlers can...

Envoy AI Proxy - MCP Message Smuggling Vulnerability

Envoy AI Gateway was found to be affected by a protocol parser differential vulnerability due to improper implementation of the JSON-RPC 2.0 specification. Such differential causes a MCP message alteration, potentially causing a bypass of security controls in a multi-layered architecture. Accordi...

eip-mcp

Exploit Intel Platform MCP Server Package/command: eip-mcp...

Failing Open

Overview n8n-mcp is an Integration between n8n workflow automation and Model Context Protocol MCP Affected versions of this package are vulnerable to Failing Open when handing multi-tenant HTTP requests ENABLEMULTITENANT=true containing one or neither of the x-n8n-url and x-n8n-key headers. An...

Spring AI MCP Security: Unvalidated URL Fetching (SSRF)

Summary The mcp-security framework fails to implement the mandatory SSRF mitigations outlined in the Model Context Protocol MCP security specifications. Specifically, it processes untrusted URLs for OAuth-related discovery and metadata without verifying if the targets are malicious or internal to...