CVE-2026-84377Medium· 6.5▾ SunlitLiteLLM 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 a…
▾ Sunlit zone — Low / medium · no exploitation signal
impact 35.8 · likelihood 0.1 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
Exploit-prediction probability, daily snapshots since Sep 9.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.3%
0.3% → 0.5%
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.
Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Affected packages:
litellm < 1.88.6litellm >= 1.89.0, < 1.89.7litellm >= 1.90.0, < 1.90.7litellm >= 1.91.0, < 1.91.5litellm >= 1.92.0, < 1.92.2litellm >= 1.93.0, < 1.93.2litellm >= 1.94.0, < 1.94.3litellm >= 1.95.0, < 1.95.1litellm >= 1.96.0, < 1.96.2Patched in:
litellm 1.88.6litellm 1.89.7litellm 1.90.7litellm 1.91.5litellm 1.92.2litellm 1.93.2litellm 1.94.3litellm 1.95.1litellm 1.96.2Connected by shared product, vendor, weakness, or advisory.
CVE-2026-114140High· 7.8nbconvert: nbconvert: arbitrary file write via path traversal in ExtractOutputPreprocessor (CVE-2026-114140)
CVE-2026-114145High· 7.5GitPython: GitPython: arbitrary code execution via improper submodule path validation (CVE-2026-114145)
CVE-2026-96644High· 7.1pillow: Pillow: Denial of Service via out-of-bounds read in metafile parser (CVE-2026-96644)
CVE-2026-114109High· 7.8uv: uv: Arbitrary code execution via path traversal in entry point names (CVE-2026-114109)
CVE-2026-92287Medium· 4.7arrow: pyarrow: arrow: Information disclosure via unvalidated KMS URLs in Parquet files (CVE-2026-92287)
CVE-2026-112892High· 7.5pillow: pillow: Denial of Service via unbounded memory expansion in MSP image decoder (CVE-2026-112892)