A critical Server-Side Request Forgery vulnerability in LibreChat allows authenticated users to bypass network restrictions and interact with internal components, posing a significant risk to infrastructure.

The application suffers from an SSRF vulnerability (CWE-918) within the Actions feature. An authenticated user can leverage the agent configuration to send requests to internal services, such as the RAG API, because the application lacks sufficient egress filtering by default.

Successful exploitation of this SSRF vulnerability permits an attacker to perform unauthorized actions against internal services that are not exposed to the public internet. With a CVSS score of 9.1, this flaw is considered critical: it could lead to the exposure of sensitive data stored in internal APIs, unauthorized modification of backend configurations, or the pivot point for further lateral movement within the network.

Immediate Action: Upgrade to the latest version of LibreChat, as the issue is addressed in version 0.8.2-rc2 and subsequent releases.

Proactive Monitoring: Review application logs for suspicious outbound HTTP requests originating from the LibreChat instance, particularly those targeting local loopback addresses or internal network subnets.

Compensating Controls: Implement strict egress filtering at the network level to prevent the application server from initiating connections to unauthorized internal infrastructure.

Public Exploit Available: No (exploit_available: unknown)

Given the critical CVSS severity and the existence of proof-of-concept evidence, immediate patching is required to secure the environment. Administrators must prioritize updating the LibreChat deployment to the latest version and verify that egress controls are enforced to prevent future SSRF-based attacks against internal services.