What is the CVSS score of CVE-2026-33265?

CVE-2026-33265 has a CVSS 3.1 base score of 6.3 (Medium). CVSS vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L. EPSS exploitation probability: 0.0%.

Which versions of Librechat are affected by CVE-2026-33265?

CVE-2026-33265 presents moderate security risk rated CVSS 6.3. Exploitation could compromise the security of affected deployments.

How to fix or mitigate CVE-2026-33265?

Within 30 days: Identify affected systems and apply vendor patches as part of regular patch cycle. Monitor vendor channels for patch availability.

Librechat CVE-2026-33265

EUVD-2026-12813 MEDIUM

Incorrect Resource Transfer Between Spheres (CWE-669)

2026-03-18 mitre

Information Disclosure Librechat

6.3

CVSS 3.1 · NVD

Severity by source

NVD PRIMARY

6.3 MEDIUM

AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L

Primary rating from NVD · only source for this CVE.

CVSS VectorNVD

CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L

Attack Vector

Local

Attack Complexity

Low

Privileges Required

Low

User Interaction

None

Scope

Changed

Confidentiality

Low

Integrity

Low

Availability

Low

Lifecycle Timeline

EUVD ID Assigned

Mar 18, 2026 - 11:30 euvd

EUVD-2026-12813

Analysis Generated

Mar 18, 2026 - 11:30 vuln.today

CVE Published

Mar 18, 2026 - 11:17 nvd

MEDIUM 6.3

DescriptionCVE.org

In LibreChat 0.8.1-rc2, a logged-in user obtains a JWT for both the LibreChat API and the RAG API.

AnalysisAI

LibreChat 0.8.1-rc2 improperly issues JWT tokens to authenticated users for both the LibreChat API and RAG API without adequate scope separation or validation, enabling token reuse across API boundaries. An authenticated attacker with local access can exploit this misconfiguration to access or manipulate resources in the RAG API using credentials intended only for the main LibreChat API. This authentication bypass affects all deployments of LibreChat 0.8.1-rc2, with a proof-of-concept available via the SBA Research advisory (EUVD-2026-12813), though no active KEV exploitation has been reported at this time.

Technical ContextAI

LibreChat is an open-source chat application that integrates with multiple backend APIs, including a dedicated Retrieval-Augmented Generation (RAG) API for document processing and context injection. The vulnerability stems from CWE-669 (Incorrect Resource Transfer Between Spheres), where JWT tokens generated for authenticated sessions in LibreChat 0.8.1-rc2 (identified via CPE cpe:2.3:a:librechat:librechat:*:*:*:*:*:*:*:*) are issued with insufficient granularity—tokens lack proper audience (aud) claims, scope restrictions, or API-specific validation. This allows a token issued for the primary API to be reused against the RAG API without the authorization layer detecting scope violations. The root cause reflects insufficient implementation of OAuth 2.0 and JWT best practices around token compartmentalization.

RemediationAI

Upgrade LibreChat to a patched version released after 0.8.1-rc2 (consult https://github.com/sbaresearch/advisories/tree/public/2025/SBA-ADV-20251205-01_LibreChat_RAG_API_Authentication_Bypass for exact recommended version). If immediate upgrade is not feasible, implement JWT validation middleware that enforces scope and audience claims at the RAG API gateway, rejecting any tokens lacking an explicit 'rag_api' audience claim. Additionally, configure the RAG API to use separate signing keys or key rotation policies distinct from the main LibreChat API to prevent token substitution. Until patching, restrict network access to the RAG API to internal-only connections and disable external RAG integration if not actively required.