Detections
Analytics
CVE-2026-22252
critical
Description
LibreChat is a ChatGPT clone with additional features. Prior to v0.8.2-rc2, LibreChat's MCP stdio transport accepts arbitrary commands without validation, allowing any authenticated user to execute shell commands as root inside the container through a single API request. This vulnerability is fixed in v0.8.2-rc2.
References
https://thehackernews.com/2026/04/anthropic-mcp-design-vulnerability.html
https://github.com/danny-avila/LibreChat/security/advisories/GHSA-cxhj-j78r-p88f
https://github.com/danny-avila/LibreChat/commit/211b39f3113d4e6ecab84be0a83f4e9c9dea127f