CVE-2026-84377
published 2026-09-02CVE-2026-84377: 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…
PriorityP342medium6.5CVSS 3.1
AVNACLPRLUINSUCHINAN
EPSS
0.31%
23.9th percentile
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.
Affected
11 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| ansible-automation-platform-26 | lightspeed-chatbot-rhel9 | — | — |
| ansible-automation-platform-27 | lightspeed-chatbot-rhel9 | — | — |
| berriai | litellm | < 1.88.6 | 1.88.6 |
| berriai | litellm | — | — |
| exploit-intelligence-tech-preview | vulnerability-analysis-rhel9 | — | — |
| lightspeed-core | lightspeed-stack-rhel9 | — | — |
| rhoai | odh-llama-stack-core-rhel9 | — | — |
| rhoai | odh-mlflow-rhel9 | — | — |
| rhoai | odh-th-torch-cpu-py312-rhel9 | — | — |
| rhoai | odh-th-torch-cuda-py312-rhel9 | — | — |
| rhoai | odh-trustyai-garak-lls-provider-dsp-rhel9 | — | — |
CVSS provenance
nvdv3.16.5MEDIUMCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
vendor_redhat6.5MEDIUM
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
Red Hat
litellm: LiteLLM: Authenticated Server-Side Request Forgery and credential exposure
vendor_redhat·2026-09-02·CVSS 6.5
CVE-2026-84377 [MEDIUM] CWE-918 litellm: LiteLLM: Authenticated Server-Side Request Forgery and credential exposure
litellm: LiteLLM: Authenticated Server-Side Request Forgery and credential exposure
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-n
VulDB
BerriAI LiteLLM up to 1.88.5/1.96.1 Request Validation auth_utils.py server-side request forgery
vuldb·2026-09-02·CVSS 6.5
CVE-2026-84377 [MEDIUM] BerriAI LiteLLM up to 1.88.5/1.96.1 Request Validation auth_utils.py server-side request forgery
A vulnerability marked as problematic has been reported in BerriAI LiteLLM up to 1.88.5/1.96.1. This vulnerability affects unknown code of the file litellm/proxy/auth/auth_utils.py of the component Request Validation. This manipulation of the argument api_base/base_url/model_list/fallbacks/litellm_credential_name causes server-side request forgery.
The identification of this vulnerability is CVE-2026-84377. It is possible to initiate the attack remotely. There is no exploit available.
It is suggested to upgrade the affected component.
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
https://github.com/BerriAI/litellm/commit/473f72e63a9777d793fbbf57194d8ec4fb97bc1bhttps://github.com/BerriAI/litellm/commit/820f247a6abba55cd87d130bef7bba7be3b29d37https://github.com/BerriAI/litellm/commit/c898d341c02299cf2506d0d8e84cc67953043593https://github.com/BerriAI/litellm/pull/36011https://github.com/BerriAI/litellm/pull/36314https://github.com/BerriAI/litellm/pull/36494https://github.com/BerriAI/litellm/releases/tag/v1.88.6https://github.com/BerriAI/litellm/releases/tag/v1.96.2https://github.com/BerriAI/litellm/security/advisories/GHSA-3cv6-jpf6-8222
2026-09-02
Published