Critical severity9.1OSV Advisory· Published Jan 12, 2026· Updated Jun 17, 2026

CVE-2026-22252

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.

AI Insight

LLM-synthesized narrative grounded in this CVE's description and references.

Affected products

Librechat/LibrechatOSV3 versions
chart-1.9.0, chart-1.9.1, chart-1.9.2, …+ 2 more
- (no CPE)range: chart-1.9.0, chart-1.9.1, chart-1.9.2, …
- cpe:2.3:a:librechat:librechat:0.8.2:rc1:*:*:*:*:*:*
- (no CPE)range: <0.8.2-rc2
osv-coords3 versions
pkg:apk/chainguard/librechat pkg:apk/chainguard/librechat-compat pkg:apk/chainguard/librechat-dev
< 0.8.01-r5+ 2 more
- (no CPE)range: < 0.8.01-r5
- (no CPE)range: < 0.8.01-r5
- (no CPE)range: < 0.8.01-r5

Patches

Vulnerability mechanics

References

github.com/danny-avila/LibreChat/commit/211b39f3113d4e6ecab84be0a83f4e9c9dea127fnvdPatch
github.com/danny-avila/LibreChat/security/advisories/GHSA-cxhj-j78r-p88fnvdExploitVendor Advisory

News mentions

No linked articles in our index yet.

cvss	0.591
epss	0.003
exploit	0.000
kev	0.000
patch	0.000
ransomware	0.000