Skip to main content
Public proof of conceptFix available

CVE-2026-32625

A public proof of concept exists; no exploitation attested.

  • Published2026-06-02
  • Fixed in0.8.4
  • WeaknessCWE-200

Am I affected?

With a domain, we read the version its public headers and pages expose. A distribution build can carry the fix under an older number.

Description

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.

Timeline

dates in UTC
  1. 2026-06-0223:16CVE publishedNVD

Observed activity

isMalicious corpus · updated 2026-10-25 15:37 UTC
Indicators tagged with this CVE, per day0 indicators over 7 days
Block these indicators
  • Firewall list (EDL, text): https://api.ismalicious.com/edl/cve/CVE-2026-32625?format=txt
  • CSV export: https://api.ismalicious.com/edl/cve/CVE-2026-32625?format=csv
  • TAXII collection of exploited CVEs
  • The EDL and CSV take an API key on the Pro plan.

Versions per branch

NVD
Librechat
BranchAffectedFixed in
0.8< 0.8.40.8.4

as publishedRanges as NVD and OSV publish them; a distribution’s build can be fixed under an older number.

Fix

  1. Update Librechat to 0.8.4

Advisories and patches

Detection

Nuclei template
none so far
ProjectDiscovery
Exploit-DB
no entry
Exploit-DB
Proof-of-concept repositories
none listed
PoC-in-GitHub

Sources

  • NVDCVE recordread 2026-10-23
  • CISA-ADPSSVC decisionpoc2026-06-03
  • OpenCVESSVC decisionpoc—
  • CNACVSS 3.19.6read 2026-10-23
  • CNAweakness (CWE)CWE-200read 2026-10-23
  • FIRST EPSSEPSS score2.9 %2026-10-25

Technical details

CVSS v3 Vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N
Published
2026-06-02
Last Modified
2026-07-22
NVD status
Analyzed

Frequently asked questions

What is CVE-2026-32625?

LibreChat is an enhanced ChatGPT clone that supports multiple AI providers. In versions up to and including 0.8.3, the Model Context Protocol (MCP) server integration resolves ${VAR} placeholders against the server's process.env during Zod schema validation of user-supplied MCP server URLs. Any authenticated user can create a malicious MCP server configuration with a URL pointing to an attacker-controlled domain containing environment variable references, causing the LibreChat server to connect to the attacker's server and transmit critical secrets such as CREDS_KEY, CREDS_IV, JWT_SECRET, and MONGO_URI in the request URL. This enables full compromise of the installation's cryptographic materials and database credentials without requiring administrative privileges. This is patched in version 0.8.4-rc1.

Is CVE-2026-32625 actively exploited?

A proof-of-concept exploit exists for CVE-2026-32625, but active exploitation has not been confirmed at this time.

What is the CVSS score for CVE-2026-32625?

CVE-2026-32625 has a CVSS v3 base score of 9.6 (CRITICAL severity), with vector string CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N.

Hear about the next vulnerability in your software

Surveillance reads the versions in your stack — a domain, a lockfile or a list — checks each CVE against the ranges its sources publish, and alerts you when one you run is exploited or enters CISA KEV. A version it cannot read stays « version not verified ».

No credit card required · No monthly cap on website lookups · 250 API requests/month