CVE-2026-84377: CWE-918: Server-Side Request Forgery (SSRF) in BerriAI litellm
Description
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to versions 1.88.6 and 1.96.2, any authenticated LiteLLM proxy user could redirect an outbound provider call to a destination the user controls and cause the proxy to send its configured provider credentials to that destination. Request validation in litellm/proxy/auth/auth_utils.py, litellm/proxy/common_request_processing.py, litellm/proxy/health_endpoints/_health_endpoints.py, litellm/proxy/image_endpoints/endpoints.py, and litellm/proxy/litellm_pre_call_utils.py used incomplete checks that did not cover every sensitive parameter or inspect equivalent values across nested request fields, path values, and bracket-notation form data. Routing and credential parameters including api_base, base_url, model_list, fallbacks, and litellm_credential_name could therefore be applied without clearing the operator's stored key, exposing upstream provider credentials and other configured secrets and permitting server-side requests to internal services reachable by the proxy. This issue is fixed in versions 1.88.6 and 1.96.2.
CVSS v3.1
Score 6.5medium
Affected software
BerriAI
litellm
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
LiteLLM is a proxy server that calls LLM APIs in OpenAI or native format. Before versions 1.88.6 and 1.96.2, authenticated users could exploit incomplete validation of routing and credential parameters (such as api_base, base_url, model_list, fallbacks, and litellm_credential_name) across multiple request processing modules. This flaw allows an attacker to redirect outbound provider calls to destinations they control, causing the proxy to send its configured provider credentials to those destinations. The vulnerability is classified as CWE-918 (Server-Side Request Forgery). The problem is fixed in versions 1.88.6 and 1.96.2.
Potential Impact
An authenticated attacker can cause the LiteLLM proxy to send its configured provider credentials to an attacker-controlled destination by redirecting outbound API calls. This leads to exposure of sensitive upstream provider credentials and potentially other configured secrets. Additionally, the attacker may leverage the SSRF to access internal services reachable by the proxy. The confidentiality of credentials is compromised, but there is no indication of integrity or availability impact.
Mitigation Recommendations
This vulnerability is fixed in LiteLLM versions 1.88.6 and 1.96.2. Users should upgrade to at least one of these versions to remediate the issue. No official patch or temporary fix is indicated beyond upgrading. Until upgraded, restrict authenticated user access to trusted parties to reduce risk.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-09-01T16:27:58.129Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6a986026acd9273b498885a4
Added to database: 09/02/2026, 17:43:02 UTC
Last enriched: 09/07/2026, 13:09:03 UTC
Last updated: 10/17/2026, 18:48:23 UTC
Views: 137
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.
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.