CVE-2025-69222
Server-Side Request Forgery in LibreChat Actions Enables Internal Access
Publication date: 2026-01-07
Last updated on: 2026-01-07
Assigner: GitHub, Inc.
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| librechat | librechat | 0.8.1-rc2 |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-918 | The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
This vulnerability is a server-side request forgery (SSRF) in LibreChat version 0.8.1-rc2 caused by missing restrictions on the Actions feature in the default configuration. LibreChat allows users to configure agents that can interact with remote services using OpenAPI specifications with various HTTP methods and authentication options. Because there are no default restrictions, these agents can access internal services, such as the RAG API included in the default Docker Compose setup, potentially allowing unauthorized internal network access.
How can this vulnerability impact me? :
This vulnerability can allow attackers or malicious agents to make unauthorized requests to internal services within the LibreChat environment. This can lead to unauthorized access to sensitive internal components, data exposure, or manipulation of internal APIs. The CVSS score of 9.1 indicates a high severity with potential impacts including high confidentiality loss, limited integrity loss, and limited availability loss.
What immediate steps should I take to mitigate this vulnerability?
Upgrade LibreChat to version 0.8.1-rc2 or later, where the SSRF vulnerability due to missing restrictions on the Actions feature is fixed. Additionally, review and restrict the Actions feature configuration to limit accessible services and prevent agents from accessing internal components.