CVE-2026-18905

IBM ContextForge MCP Gateway mcp-contextforge-gateway = v1.0.6 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive information due to a DNS rebinding vulnerability during tool invocation...

CVE-2026-18905

IBM ContextForge MCP Gateway (mcp-contextforge-gateway) versions up to v1.0.6 are vulnerable to a DNS rebinding attack that enables server-side request forgery (SSRF) . The gateway validates REST tool target URLs only once at tool-registration time; when the same tool is later invoked, the stored...

CVE-2026-18905 IBM ContextForge MCP Gateway is affected by server-side request forgery via DNS TOCTOU at tool invocation

IBM ContextForge MCP Gateway mcp-contextforge-gateway = v1.0.6 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive information due to a DNS rebinding vulnerability during tool invocation...

EUVD-2026-71315

IBM ContextForge MCP Gateway mcp-contextforge-gateway = v1.0.6 MCP Context Forge could allow a remote authenticated attacker to obtain sensitive information due to a DNS rebinding vulnerability during tool invocation...

Security Bulletin: IBM ContextForge MCP Gateway is affected by server-side request forgery via DNS TOCTOU at tool invocation

Summary IBM ContextForge MCP Gateway mcp-contextforge-gateway validates REST tool target URLs for server-side request forgery SSRF only once, at tool-registration time. When the same tool is later invoked, the stored URL is used directly without re-validation or DNS-resolution pinning, allowing a...

CVE-2026-81102 Dropbox Dash MCP Server DNS Rebinding via Missing Host Header Validation

The Dash MCP server bound its listener to the loopback address but never checked the host a request named. src/mcpserverdash.py constructed the server for its network mode with the interface restricted to loopback and no transport-security settings, so a name that had been pointed at the loopback...

CVE-2026-59318

In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege...

CVE-2026-72681 Missing Authorization in Kibana Leading to Privilege Escalation and Information Disclosure

Kibana Agent Builder does not correctly verify that the requesting user holds the privileges required by a separate Kibana feature before it creates and runs a tool that invokes that feature's functionality. This allows privilege escalation and could lead to disclosure of sensitive information th...

CVE-2026-14537

Incorrect Authorization in the direct HTTP API tool invocation endpoint in Google mcp-toolbox versions v1.3.0 and v1.4.0 allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature via sending tool invocation requests through legacy HTTP endpoints when the --enable-a...

CVE-2026-14537

The CVE-2026-14537 entry concerns Google mcp-toolbox versions v1.3.0 and v1.4.0 with Incorrect Authorization in the direct HTTP API tool invocation endpoint. The underlying issue allows an unauthenticated attacker to invoke tools protected by the scopeRequired feature by sending tool invocation r...

CVE-2026-9680 MCP Server Exposure via Insecure Default Binding on alibabacloud-rds-openapi-mcp-server

Improper exposure of the MCP server in alibabacloud-rds-openapi-mcp-server allows remote attackers to invoke exposed MCP tools via network access to an MCP endpoint listening on all network interfaces by default...

CVE-2026-61427

PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream'...

CVE-2026-61427

PraisonAI before 4.6.78 has an authentication bypass in the MCP HTTP-stream transport: running with --transport http-stream and no API key allows unauthenticated clients to initialize sessions, enumerate tools (tools/list), and invoke tools (tools/call). The dispatcher forwards tool-call argument...

EUVD-2026-44638

PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream'...

CVE-2026-61427

PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream'...

CVE-2026-61427 PraisonAI before 4.6.78 Authentication Bypass via HTTP-stream

PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api-key option defaults to None, and the server only enforces Authorization/Bearer checks when an API key is configured. When an operator runs 'praisonai mcp serve --transport http-stream'...

PYSEC-2026-2579 Langroid: handle_message() executes user-supplied tool JSON without sender verification

Summary A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Details enablemessage..., use=False, handle=True only prevents the LLM from being instructed to generate...

CVE-2026-54771

Langroid prior to 0.65.3 is affected. A Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Root cause: the tool dispatch path in agent_response → handle_message → get...

CVE-2026-54771

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Version...

CVE-2026-54771 Langroid: handle_message() executes user-supplied tool JSON without sender verification

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.65.3, a Langroid application exposing a chat interface to untrusted users may allow direct tool invocation via raw JSON payloads, even when tools are registered with use=False, handle=True. Version...