← Back
CVE-2026-59820 medium CVSS 6.5

Path Traversal in litellm (CVE-2026-59820)

Summary

path traversal in litellm (CVE-2026-59820). Data can be tampered with by attackers. Exploitable via `POST /v1/skills`. Mitigation: upgrade to `1.83.7-stable` or later.

AI summary snake-internal / snake-material-v2

A vulnerability tracked as **CVE-2026-59820** has been found in litellm. Attackers can target a specific entry point like `POST /v1/skills` over the network to misuse the product. Data can be tampered with by attackers. CVSS score: 6.5/10. What to do: upgrade litellm to **1.83.7-stable** or later. If unsure, ask your IT team or search "litellm CVE-2026-59820" on the vendor's site.
CVE-2026-59820 (litellm) — CWE-22 / CVSS v3 6.5 Attack vector: remote (network-reachable) / no user interaction Attack surface: POST /v1/skills / `allowed_routes` / `anthropic_routes` / `llm_api_routes` Patched: `1.83.7-stable` — apply immediately Workaround: 1. Block `POST /v1/skills` at your reverse proxy or API gateway. 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
**Path traversal** (CWE-22) exists in litellm. Attackers reach the vulnerable code path via `POST /v1/skills` without authentication.
📍 Affected scope
litellm — . Attack surface: POST /v1/skills / `allowed_routes` / `anthropic_routes` / `llm_api_routes`.
🔥 Severity
Severity: Medium (CVSS 6.5/10). Data can be tampered with by attackers
🔧 How to fix
Update to **1.83.7-stable**.
🛡️ Workaround
Workaround: 1. Block `POST /v1/skills` at your reverse proxy or API gateway.
🔍 Detection
Search webserver/proxy logs for unusual `POST /v1/skills` 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

  1. 1
    Identify 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。

  2. 3
    Hunt for indicators of compromise detect
    grep 'POST /v1/skills' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'

    アクセスログで `POST /v1/skills` 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。

  3. 5
    Apply temporary workaround mitigate
    1. Block `POST /v1/skills` at your reverse proxy or API gateway.

    パッチが適用されるまでの応急処置として、1. Block `POST /v1/skills` at your reverse proxy or API gateway. を実施。回避策の副作用 (機能低下) を確認した上で。

  4. 6
    Apply patch patch
    Upgrade litellm to 1.83.7-stable

    ステージング環境で 1.83.7-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。

  5. 7
    Post-deployment verification verify
    Replay attack against POST /v1/skills 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

pip litellm
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"1.83.7"}]}]

References

🍪 About cookies

We use cookies to keep you logged in, remember your language, and improve the service.

Details →