Description
LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.
Published: 2026-03-27
Score: 7.7 High
EPSS: n/a
KEV: No
Impact: Server‑Side Request Forgery exposing internal resources
Action: Patch Immediately
AI Analysis

Impact

LibreChat versions 0.8.2‑rc2 through 0.8.2 contain a Server‑Side Request Forgery weakness (CWE‑918) that allows an attacker to supply a URL via agent actions or MCP and have the server resolve it without checking for private addresses. The result is that LibreChat can reach internal endpoints such as a private RAG API or cloud instance metadata services, potentially exposing sensitive data or enabling further attacks. The CVSS base score of 7.7 reflects the ability to obtain data without authentication and to impact confidentiality and integrity.

Affected Systems

The affected product is LibreChat released by the vendor 'danny‑avila'. Affected versions are 0.8.2‑rc2 through 0.8.2 inclusive. A fix that restores proper DNS validation and prevents access to private IPs is available in version 0.8.3‑rc1. No other product or vendor information is provided.

Risk and Exploitability

The likely attack vector is remote network access where an attacker can send a crafted request to LibreChat through its chat interface or API. Because the service lacks private‑IP filtering, an attacker can reach internal resources, securing sensitive data or credentials. The CVSS score of 7.7 indicates a high severity, and the lack of an EPSS score for this vulnerability does not diminish its potential impact. Since the vulnerability is not listed in CISA’s KEV catalog, no known exploits are publicly documented, but the presence of the flaw and the high score suggest that monitoring and rapid mitigation are prudent.

Generated by OpenCVE AI on March 27, 2026 at 20:21 UTC.

Remediation

No vendor fix or workaround currently provided.

OpenCVE Recommended Actions

  • Upgrade LibreChat to version 0.8.3‑rc1 or later.
  • If upgrading is not immediately possible, disable or restrict the use of agent actions or MCP that trigger outbound requests.
  • Implement monitoring for unexpected outbound connections from the LibreChat server.

Generated by OpenCVE AI on March 27, 2026 at 20:21 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Fri, 27 Mar 2026 19:45:00 +0000

Type Values Removed Values Added
Description LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.
Title LibreChat Server-Side Request Forgery using DNS resolution
Weaknesses CWE-918
References
Metrics cvssV3_1

{'score': 7.7, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N'}


Subscriptions

No data.

cve-icon MITRE

Status: PUBLISHED

Assigner: GitHub_M

Published:

Updated: 2026-03-27T19:24:30.707Z

Reserved: 2026-03-10T15:10:10.656Z

Link: CVE-2026-31945

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-03-27T20:16:30.060

Modified: 2026-03-27T20:16:30.060

Link: CVE-2026-31945

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-03-27T20:27:34Z

Weaknesses