Server-Side Request Forgery Vulnerability in LibreChat by Danny Avila
CVE-2026-31945

7.7HIGH

Key Information:

Vendor

Danny-avila

Status
Librechat
Vendor
CVE Published:
27 March 2026

What is CVE-2026-31945?

LibreChat, a ChatGPT clone with unique features, is vulnerable to a server-side request forgery (SSRF) attack in its versions 0.8.2-rc2 and 0.8.2. This vulnerability arises when utilizing agent actions or MCP, allowing attackers to exploit a flaw in the hostname validation process. Although a previous advisory addressed a related SSRF risk, the implemented fix failed to fully validate DNS resolutions against private IP addresses. Consequently, attackers can potentially access sensitive internal resources, including an internal RAG API or cloud instance metadata endpoints. Users are encouraged to update to version 0.8.3-rc1, which includes a critical patch to address this issue.

Affected Version(s)

LibreChat >= 0.8.2-rc2, < 0.8.3-rc1

References

https://github.com/danny-avila/LibreChat/security/advisor...
x_refsource_CONFIRM

CVSS V3.1

Score:
7.7
Severity:
HIGH
Confidentiality:
High
Integrity:
None
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
Low
User Interaction:
None
Scope:
Changed

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.