---
id: CVE-2026-67531
title: FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP)
summary: "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 n…"
severity: none
cwe:
  - CWE-94
published: '2026-08-06'
updated: '2026-09-10'
sourceUpdated: '2026-09-10T20:37:00.427'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-67531'
references:
  - url: >-
      https://github.com/agentfront/frontmcp/commit/209cddd19a8d4db0777f725b527818da7df6f67f
    label: security-advisories@github.com
  - url: >-
      https://github.com/agentfront/frontmcp/security/advisories/GHSA-mp29-fxh8-92px
    label: security-advisories@github.com
  - url: >-
      https://github.com/agentfront/frontmcp/security/advisories/GHSA-mp29-fxh8-92px
    label: 134c704f-9b21-4f2e-91b3-4a467353bcc0
tags:
  - nvd
epss: 0.00735
epssPercentile: 0.52469
ingestedAt: '2026-09-10T21:05:53.593Z'
---

## Overview

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 invariants force the security membrane to hand back the raw host object, letting a script reach _zod.constr.constructor (the host Function constructor) and execute arbitrary code in the server process. A single tools/call is sufficient to escape the sandbox and achieve remote code execution as the server user, exposing everything the process holds such as OAuth client secrets, JWT_SECRET, session keys, database credentials, and cloud instance metadata. Because the framework's DEFAULT_AUTH_OPTIONS is public mode, an unconfigured server serves this to unauthenticated callers, and on authenticated servers an indirect prompt injection in tool output or fetched content can trigger it without a human attackerThis issue is fixed in version 1.5.7.

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.