p PatchFirst

PatchFirst · Latest vulnerabilities

mcp-contextforge-gateway vulnerabilities

Vulnerabilities published for mcp-contextforge-gateway in the last 30 days: 0. Listed in the KEV catalogue: 0.

Filter vulnerabilities
Clear filters

Vulnerabilities: 3

  1. CVE-2026-53710

    Critical · CVSS 10EPSS 1.14%Fix available

    MCP Context Forge: RestrictedPython sandbox bypass via getattr builtin in python_sandbox_server

    MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the python_sandbox_server in mcp-servers/python/python_sandbox_server/src/python_sandbox_server/server_fastmcp.py exposes raw getattr through safe_builtins, omits a required _getattr_ guard, and relies on validate_code checks for literal dangerous dunder strings. An attacker can construct dunder names at runtime, traverse the Python class hierarchy, reach subprocess.Popen, and execute OS commands with the server process privileges through the execute_code MCP tool. The HTTP/SSE transport can expose this tool without authentication, while

    • Update to 1.0.2
    Published Updated
  2. CVE-2026-53708

    Medium · CVSS 6.6EPSS 0.35%Fix available

    ContextForge: DNS TOCTOU race condition causes SSRF protection bypass (`/admin/gateways/test`)

    ContextForge is an AI gateway, registry, and proxy that provides centralized discovery, guardrails, and management for MCP, A2A, and REST or gRPC APIs. Prior to 1.0.3, the /admin/gateways/test call site in mcpgateway/admin.py calls validate_gateway_test_url() in mcpgateway/common/validators.py to resolve and reject private, loopback, link-local, and cloud-metadata addresses, but ResilientHttpClient later resolves the original hostname again without binding the validated address. When MCPGATEWAY_ADMIN_API_ENABLED is enabled, an attacker with a database-backed role containing explicit gateways.read permission can use DNS rebinding to return a p

    • Update to 1.0.3
    Published Updated
  3. GHSA-vwf3-4xxj-qg6h

    Not ratedFix available

    mcp-contextforge-gateway has Server-Side Template Injection (SSTI) leading to Remote Code Execution in `PromptService._render_template` via unsandboxed Jinja2 Environment

    ### Summary `mcpgateway.services.prompt_service.PromptService` renders user-supplied prompt templates using Jinja2's plain `Environment()` rather than `SandboxedEnvironment`. An authenticated user with permission to register or update prompt templates can store a malicious template that, on subsequent rendering, executes arbitrary Python code on the gateway host with the privileges of the gateway process. This is a Server-Side Template Injection (SSTI) vulnerability leading to Remote Code Execution. ### Details **Affected component:** `mcpgateway/services/prompt_service.py` **Affected version:** `0.9.0` (verified). The fix in the unrelease

    • Update to 1.0.0
    Published Updated

Check your server

Check your installed stack and versions against the current vulnerability feeds.

Check your server →