Vulnerability in litellm (CVE-2026-59819)
Summary
Vulnerability in litellm (CVE-2026-59819). Confidential information can be exposed externally. Exploitable via litellm_params. Mitigation: upgrade to 1.83.10-stable or later.
Original description
The description as published by the source.
LiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. Prior to 1.83.10-stable, LiteLLM's /health/test_connection endpoint resolved request-supplied environment and OIDC file references in litellm_params, allowing a proxy administrator or another privileged caller with permission to test model connections to read files from the local filesystem via an oidc/file/ reference. This issue is fixed in version 1.83.10-stable.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-59819 has been found in litellm.
Attackers can target a specific entry point like litellm_params over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: 4.9/10.
What to do: upgrade litellm to 1.83.10-stable or later.
If unsure, ask your IT team or search "litellm CVE-2026-59819" on the vendor's site.
CVE-2026-59819 (litellm) — CWE-73 / CVSS v3 4.9
Attack vector: remote (network-reachable) / no user interaction
Attack surface: litellm_params
Patched: 1.83.10-stable — apply immediately
Workaround: Restrict /health/test_connection access to trusted administrators only.
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
A vulnerability (CWE-73) exists in litellm. Attackers reach the vulnerable code path via litellm_params.
Check the vendor advisory for the affected versions of litellm. Attack surface: litellm_params.
Severity: Medium (CVSS 4.9/10). Confidential information can be exposed externally.
Update to 1.83.10-stable.
Workaround: Restrict /health/test_connection access to trusted administrators only.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'litellm' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'litellm' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
litellmを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply temporary workaround mitigate
Restrict `/health/test_connection` access to trusted administrators only.パッチが適用されるまでの応急処置として、Restrict
/health/test_connectionaccess to trusted administrators only. を実施。回避策の副作用 (機能低下) を確認した上で。 -
3Apply patch patch
Upgrade litellm to 1.83.10-stableステージング環境で 1.83.10-stable に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
4Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory github.com
- advisory github.com
- package github.com
- package pypi.org
- patch github.com
- web github.com