Sensitive Data Exposure Vulnerability in LibreChat by Danny Avila
CVE-2026-44653

6.5MEDIUM

Key Information:

Vendor

Danny-avila

Status
Librechat
Vendor
CVE Published:
2 June 2026

What is CVE-2026-44653?

LibreChat, a ChatGPT clone that integrates various AI providers, is susceptible to a vulnerability that allows users with view-only access to an MCP server to access its decrypted admin-managed secrets. Specifically, versions up to and including 0.8.3 expose critical information via the GET API calls for server configurations. Attackers can retrieve sensitive data, such as 'apiKey.key' and 'oauth.client_secret', enabling the potential for credential exfiltration from a shared server setup. To mitigate this risk, updated practices should include not returning plaintext secrets to unauthorized users, masking sensitive information in API responses, and utilizing secure server-side storage for credentials, returning only placeholders when necessary. Version 0.8.4 has been patched to address these security concerns.

Affected Version(s)

LibreChat < 0.8.4

References

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

CVSS V3.1

Score:
6.5
Severity:
MEDIUM
Confidentiality:
High
Integrity:
None
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Privileges Required:
Low
User Interaction:
None
Scope:
Unchanged

Timeline

  • Vulnerability published

  • Vulnerability Reserved

.