← Back
CVE-2024-6587
SSRF (Server-Side Request Forgery) in litellm (CVE-2024-6587)
Summary
SSRF in litellm (CVE-2024-6587). Confidential information can be exposed externally. Exploitable via `POST /chat/completions`. Mitigation: upgrade to `1.44.8` or later.
AI summary snake-internal / snake-material-v2
A vulnerability tracked as **CVE-2024-6587** has been found in litellm.
Attackers can target a specific entry point like `POST /chat/completions` over the network to misuse the product.
Confidential information can be exposed externally. CVSS score: ?/10.
What to do: upgrade litellm to **1.44.8** or later.
If unsure, ask your IT team or search "litellm CVE-2024-6587" on the vendor's site.
CVE-2024-6587 (litellm) — CWE-918 /
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /chat/completions / `api_base`
Patched: `1.44.8` — apply immediately
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.
❓ What is the problem
**SSRF** (CWE-918) exists in litellm. Attackers reach the vulnerable code path via `POST /chat/completions` without authentication.
📍 Affected scope
litellm — . Attack surface: POST /chat/completions / `api_base`.
🔥 Severity
Severity: ?. Confidential information can be exposed externally
🔧 How to fix
Update to **1.44.8**.
🛡️ Workaround
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
🔍 Detection
Search webserver/proxy logs for unusual `POST /chat/completions` requests with malformed payloads or SQL meta-characters. Run `grep -r 'litellm' .` against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response Actions (7 steps)
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。
-
3Hunt for indicators of compromise detect
grep 'POST /chat/completions' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで `POST /chat/completions` への異常なリクエスト (不正な認証ヘッダ・SQLメタ文字)を過去 30〜90日分捜索。WAF/SIEM があれば該当パスのアラート発火履歴を確認。
-
6Apply patch patch
Upgrade litellm to 1.44.8ステージング環境で 1.44.8 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と、Step 3 で見つけた異常検知の続報チェックを含めること。
-
7Post-deployment verification verify
Replay attack against POST /chat/completions on staging to confirm patch closes the vector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 Step 3 と同じログクエリでアラート再発が無いか継続監視。
Affected packages
PyPI
litellm
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"1.44.8"}]}]
References
- advisory https://nvd.nist.gov/vuln/detail/CVE-2024-6587
- advisory https://github.com/advisories/GHSA-g26j-5385-hhw3
- package https://github.com/berriai/litellm
- package https://pypi.org/project/litellm
- web https://github.com/berriai/litellm/commit/ba1912afd1b19e38d3704bb156adf887f91ae1e0
- web https://huntr.com/bounties/4001e1a2-7b7a-4776-a3ae-e6692ec3d997