Information disclosure in Danny-Avila Librechat
CVE-2026-31951
LibreChat is a ChatGPT clone with additional features. In versions 0.8.2-rc1 through 0.8.3-rc1, user-created MCP (Model Context Protocol) servers can include arbitrary HTTP headers that undergo credential placeholder substitution. An attacker can create a malicious MCP server with headers containing `{{LIBRECHAT_OPENID_ACCESS_TOKEN}}` (and others), causing victims who call tools on that server to have their OAuth tokens exfiltrated. Version 0.8.3-rc2 fixes the issue.
Vulnerability class: Information Disclosure
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.8 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:C/C:H/I:N/A:N.
EPSS exploit prediction
EPSS: 0.004 (26.4th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 26th percentile — 26.4% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.002 · newest: 0.004 · change: +0.001
Affected products
- Danny-Avila Librechat — versions >= v0.8.2-rc1, <= v0.8.3-rc1
- Librechat — versions 0.8.3
Weakness classification (CWE)
References
- github.com/danny-avila/LibreChat/security/advisories/GHSA-pmw7-gqwj-f954 (Exploit, Vendor Advisory)
Frequently asked questions
- What is CVE-2026-31951?
- CVE-2026-31951 is a medium-severity vulnerability in Danny-Avila Librechat, classified under Information Disclosure. CVSS score: 6.8/10. Published 2026-03-27.
- How severe is CVE-2026-31951?
- Medium severity. CVSS v3 base score is 6.8 out of 10.