CVE-2026-31945: CWE-918: Server-Side Request Forgery (SSRF) in danny-avila LibreChat
LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.
AI Analysis
Technical Summary
CVE-2026-31945 is a server-side request forgery (SSRF) vulnerability in the danny-avila LibreChat product, specifically affecting versions from 0.8.2-rc2 up to but not including 0.8.3-rc1. The vulnerability occurs when using agent actions or MCP features. Although a prior SSRF vulnerability was patched by adding hostname validation, this fix did not verify whether the DNS resolution pointed to private IP addresses. Consequently, attackers can exploit this to access internal resources such as internal RAG APIs or cloud instance metadata endpoints. The vulnerability has a CVSS 3.1 score of 7.7 (high severity) with network attack vector, low attack complexity, requiring low privileges and no user interaction, and impacts confidentiality with scope change. The issue is fixed in version 0.8.3-rc1.
Potential Impact
Successful exploitation allows an attacker to perform SSRF attacks that can access internal network resources and sensitive endpoints such as cloud instance metadata services. This can lead to unauthorized disclosure of sensitive information within the internal network environment. The vulnerability does not affect integrity or availability directly but has a high confidentiality impact and changes the security scope.
Mitigation Recommendations
Upgrade affected LibreChat instances to version 0.8.3-rc1 or later, which contains the patch addressing this SSRF vulnerability by properly validating DNS resolution results to prevent access to private IP addresses. No other mitigations are indicated by the vendor advisory.
CVE-2026-31945: CWE-918: Server-Side Request Forgery (SSRF) in danny-avila LibreChat
Description
LibreChat is a ChatGPT clone with additional features. Versions 0.8.2-rc2 through 0.8.2 are vulnerable to a server-side request forgery (SSRF) attack when using agent actions or MCP. Although a previous SSRF vulnerability (https://github.com/danny-avila/LibreChat/security/advisories/GHSA-rgjq-4q58-m3q8) was reported and patched, the fix only introduced hostname validation. It does not verify whether DNS resolution results in a private IP address. As a result, an attacker can still bypass the protection and gain access to internal resources, such as an internal RAG API or cloud instance metadata endpoints. Version 0.8.3-rc1 contains a patch.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-31945 is a server-side request forgery (SSRF) vulnerability in the danny-avila LibreChat product, specifically affecting versions from 0.8.2-rc2 up to but not including 0.8.3-rc1. The vulnerability occurs when using agent actions or MCP features. Although a prior SSRF vulnerability was patched by adding hostname validation, this fix did not verify whether the DNS resolution pointed to private IP addresses. Consequently, attackers can exploit this to access internal resources such as internal RAG APIs or cloud instance metadata endpoints. The vulnerability has a CVSS 3.1 score of 7.7 (high severity) with network attack vector, low attack complexity, requiring low privileges and no user interaction, and impacts confidentiality with scope change. The issue is fixed in version 0.8.3-rc1.
Potential Impact
Successful exploitation allows an attacker to perform SSRF attacks that can access internal network resources and sensitive endpoints such as cloud instance metadata services. This can lead to unauthorized disclosure of sensitive information within the internal network environment. The vulnerability does not affect integrity or availability directly but has a high confidentiality impact and changes the security scope.
Mitigation Recommendations
Upgrade affected LibreChat instances to version 0.8.3-rc1 or later, which contains the patch addressing this SSRF vulnerability by properly validating DNS resolution results to prevent access to private IP addresses. No other mitigations are indicated by the vendor advisory.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-03-10T15:10:10.656Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 69c6de373c064ed76fea1d65
Added to database: 3/27/2026, 7:44:55 PM
Last enriched: 4/4/2026, 10:58:34 AM
Last updated: 5/12/2026, 3:37:24 PM
Views: 50
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.