CVE-2026-32625: LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the M
Summary
LibreChat, a ChatGPT-like tool that works with multiple AI providers, has a vulnerability in versions up to 0.8.3 where it unsafely replaces environment variable placeholders (like ${VAR}) when validating user-provided server URLs. An authenticated attacker can create a malicious server configuration that tricks LibreChat into sending sensitive secrets like encryption keys and database credentials to an attacker-controlled server, compromising the entire installation without needing admin access.
Solution / Mitigation
This is patched in version 0.8.4-rc1.
Vulnerability Details
9.6(critical)
EPSS: 0.0%
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
network
low
low
none
June 2, 2026
Classification
Taxonomy References
Affected Vendors
Related Issues
Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-32625
First tracked: June 2, 2026 at 08:09 PM
Classified by LLM (prompt v3) · confidence: 92%