Vulnerability · Published Aug 25, 2026 · Assigned by GitHub_M

CVE-2026-45018Chainlit: Command injection via MCP stdio transport allows unauthenticated remote code execution

Critical 9.8

In plain English

A critical-severity OS command injection in chainlit from Chainlit. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 1.1% (higher than 65% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)9.8Critical
Exploit odds (30 days)1.1%top 34.6% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

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 packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIchainlit2.12.0GHSA-w3fx-mc44-mf6j
PyPIchainlit2.12.0PYSEC-2026-3812

Affected products (as reported)

VendorProductVersions
Chainlit chainlit >= 2.4.0rc0, < 2.12.0

Weakness: CWE-78 · Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References