CVE-2026-45018
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.
References
- https://github.com/Chainlit/chainlit/blob/2.12.0/docs/security-advisory-2026-mcp.md#spl-2026-001--command-injection-via-mcp-stdio
- https://github.com/Chainlit/chainlit/commit/0565fd0eccb915fce159929598b053ed79f6e0c9
- https://github.com/Chainlit/chainlit/releases/tag/2.12.0
- https://github.com/Chainlit/chainlit/security/advisories/GHSA-w3fx-mc44-mf6j
- https://github.com/Chainlit/chainlit/security/advisories/GHSA-w3fx-mc44-mf6j