HighVulnerabilityLLM-specific

CVE-2026-54033: LibreChat server-side request forgery through custom OpenAI-compatible baseURL

Source: NVD(opens in a new tab)
Identifier: CVE-2026-54033
Published: June 25, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.4%

Summary

CVE-2026-54033 affects LibreChat versions prior to 0.8.4-rc1. Authenticated users can set the baseURL for custom OpenAI-compatible endpoints, and LibreChat sends HTTP requests to that URL without SSRF validation, so the baseURL can point at internal network addresses. The weakness is classified as CWE-918.

Mitigation

Fixed in 0.8.4-rc1.

Details

Scores and exploitation

CVSS score: 7.7(high)
CVSS vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
Attack vector: network
Attack complexity: low
Privileges required: low
User interaction: none
EPSS: 0.4%Estimated probability that this CVE is exploited in the next 30 days, from the FIRST Exploit Prediction Scoring System. Read on November 9, 2026.
Disclosure date: June 25, 2026

Weaknesses and techniques

Weakness (CWE): CWE-918
Attack pattern (CAPEC): CAPEC-664

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: API
Impact: Confidentiality,
Integrity
Labels: security

How this record was produced

Summaries, mitigations and labels on this page are generated automatically from the source. The linked source is authoritative. The source gives this advisory a description and no title, so the title above is a headline generated from the source text.

Original source: https://nvd.nist.gov/vuln/detail/CVE-2026-54033

First tracked: June 25, 2026 at 02:11 PM ET, from NVD/CVE Database

Classifier: claude-haiku-5-5, prompt v4

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items