CVE-2026-45018

published 25 Aug 2026 · updated 25 Aug 2026

Chainlit: Command injection via MCP stdio transport allows unauthenticated remote code execution

9.8CriticalCVSS 9.8EPSS 1%

No exploitation in the wild has been reported. EPSS puts the chance of exploitation in the next 30 days at 1%. No fixed version is recorded.

Chainlit is a Python framework for building production-ready conversational AI applications. From 2.4.0rc0 until 2.12.0, Chainlit deployments with features.mcp.enabled set to true in .chainlit/config.toml expose the POST /mcp endpoint without requiring authentication. For stdio transport, the endpoint accepts a user-controlled fullCommand string. The validate_mcp_command() function in backend/chainlit/mcp.py checks only the executable name against config.features.mcp.stdio.allowed_executables and passes unchecked arguments to StdioServerParameters in backend/chainlit/server.py. Because npx supports the -c argument, an attacker can execute arbitrary shell commands with the privileges of the Chainlit process. If allowed_executables is unset, its None default is treated as allowing every executable. This issue is fixed in version 2.12.0.

Affected

Vendors, products and packages with version ranges

VendorProductVersionsFixed
Chainlit>=2.4.0rc0 <2.12.0

Timeline

Every event on this vulnerability

Embed

A live severity badge for an advisory, README or ticket

CVE-2026-45018 severity on Zeptric[![CVE-2026-45018](https://zeptric.io/badge/cve/CVE-2026-45018.svg)](https://zeptric.io/cve/CVE-2026-45018)