MediumVulnerabilityLLM-specific

CVE-2026-31950: LibreChat SSE streaming endpoint exposes other users' chat content

Source: NVD(opens in a new tab)
Identifier: CVE-2026-31950
Published: March 27, 2026
Record updated: October 9, 2026

Known exploitation: Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
EPSS: 0.2%

Summary

CVE-2026-31950 affects LibreChat in versions 0.8.2-rc2 through 0.8.2-rc3. The SSE streaming endpoint `/api/agents/chat/stream/:streamId` does not check that the requesting user owns the stream, so any authenticated user holding a valid stream ID can subscribe and read another user's real-time chat content, including messages, AI responses and tool invocations. The weakness is classified as CWE-284, Improper Access Control.

Mitigation

Version 0.8.2 patches the issue.

Details

Scores and exploitation

CVSS score: 5.3(medium)
CVSS vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:N/A:N
Attack vector: network
Attack complexity: high
Privileges required: low
User interaction: none
EPSS: 0.2%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: March 27, 2026

Weaknesses and techniques

Weakness (CWE): CWE-284

Classification

Attack type: Other
Attack sophistication: Trivial
AI component targeted: Inference
Impact: Confidentiality
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-2026-31950

First tracked: March 28, 2026 at 02:07 AM ET, from NVD/CVE Database

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

Classifier confidence: 90% (self-assessed)

Summary

Mitigation

Related items