MCP Inspector < 0.14.0 UnauthenticatedRemote Code Execution

The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. id...

CVE-2026-48039

CVE-2026-48039 : In Meta Ads MCP, versions before 1.0.109 suffer an authentication bypass where AuthInjectionMiddleware.dispatch() forwards unauthenticated /mcp requests to tool handlers, and when no per-request credential exists, falls back to META_ACCESS_TOKEN. The downstream Graph API error pa...

CVE-2026-70639

llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench1model function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger ...

CVE-2026-70639

llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench1model function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger ...

EUVD-2026-53684

FrontMCP is a TypeScript-first framework for the Model Context Protocol MCP. Prior to 1.5.7, the sandboxed codecall:execute tool exposes live host Zod schema instances to the script via getTool, and because Zod v4 defines zod as a non-configurable, non-writable own property, the ECMAScript Proxy...

CVE-2026-17625

Langflow OSS versions 1.0.0–1.10.3 are affected by an OS Command Injection in Model Context Protocol features (MCP). The IBM bulletin describes weaknesses in MCP validation, authentication/authorization enforcement, and request handling that could allow a remote authenticated attacker to execute ...

CVE-2026-17625 Langflow is affected by OS Command Injection in Model Context Protocol features

IBM Langflow OSS 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, 1.0.0 through 1.10.3, and 1.0.0 through 1.10.3 could allow a remote authenticated attacker to execute arbitrary commands due to improper neutralization of special element...

CVE-2026-8446

IBM Langflow OSS 1.0.0 through 1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol MCP composer endpoint when mcpcomposerenabled=true default and projects are configured with authtype=oauth...

CVE-2026-17623

Langflow OSS 1.0.0–1.10.3 is affected by CVE-2026-17623: a remote authenticated attacker can execute arbitrary commands due to improper validation of the command field in MCP server configurations. Affected product is Langflow OSS (versions 1.0.0–1.10.3). The root cause is inadequate validation o...

CVE-2026-17623 Langflow is affected OS Command Injection in Model Context Protocol features

IBM Langflow OSS 1.0.0 through 1.10.3 could allow a remote authenticated attacker to execute arbitrary commands due to improper validation of the command field in MCP server configurations...

CVE-2026-17630

Langflow OSS 1.0.0–1.10.3 is affected by CVE-2026-17630, where improper validation of configuration parameters could allow a remote attacker to execute arbitrary code. The issue pertains to Langflow OSS components handling MCP/configuration inputs, enabling code execution with network access and ...

CVE-2026-17630 Langflow is affected by security vulnerabilities in Model Context Protocol features

IBM Langflow OSS 1.0.0 through 1.10.3 could allow a remote attacker to execute arbitrary code due to improper validation of configuration parameters...

CVE-2026-17626 Langflow is affected by security vulnerabilities in Model Context Protocol features

IBM Langflow OSS 1.0.0 through 1.10.3 Langflow could allow an authenticated attacker to read, modify, or expose sensitive host files via Docker-based MCP servers due to incomplete filtering of dangerous Docker volume-mount and device-mapping arguments...

CVE-2026-17626

CVE-2026-17626 affects IBM Langflow OSS versions 1.0.0–1.10.3. An authenticated attacker could read, modify, or expose sensitive host files through Docker-based MCP servers due to incomplete filtering of dangerous docker volume-mount and device-mapping arguments. The IBM/NVD entries describe the ...

CVE-2026-8446

Langflow OSS versions 1.0.0–1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol (MCP) composer endpoint when mcp_composer_enabled=true (default) and projects use auth_type=oauth. The issue, tracked under CVE-2026-8446, enables bypassing authentication for the MCP c...

EUVD-2026-53465

IBM Langflow OSS 1.0.0 through 1.10.3 contain an authentication bypass vulnerability in the Model Context Protocol MCP composer endpoint when mcpcomposerenabled=true default and projects are configured with authtype=oauth...

CVE-2026-7646

CVE-2026-7646 affects IBM Langflow OSS 1.0.0–1.10.3. Affected component: Model Context Protocol (MCP) resources/read handling. Root cause: URL-encoded path traversal in the filename enables a crafted MCP request to read arbitrary server files (including other users’ documents, JWT signing secret,...

Security Bulletin: Langflow is affected by security vulnerabilities in Model Context Protocol features

Summary Langflow uses Model Context Protocol MCP features to manage external server connections, project access, file resources, and local client integration. Weaknesses in MCP command and configuration validation, authentication and authorization enforcement, file resource handling, and request...

CVE-2026-12940

IBM Langflow OSS 1.0.0 through 1.10.1 are vulnerable to unauthenticated remote code execution via environment variable injection in the MCP Model Context Protocol stdio launcher. The vulnerability exists in src/lfx/src/lfx/base/mcp/util.py where the DANGEROUSENVVARS blocklist fails to include...

CVE-2026-12940

IBM Langflow OSS 1.0.0 through 1.10.1 are vulnerable to unauthenticated remote code execution via environment variable injection in the MCP Model Context Protocol stdio launcher. The vulnerability exists in src/lfx/src/lfx/base/mcp/util.py where the DANGEROUSENVVARS blocklist fails to include...