← Back
CVE-2025-48944
Vulnerability in vllm (CVE-2025-48944)
Summary
vulnerability in vllm (CVE-2025-48944). Risk of unauthorized operations or information disclosure. Exploitable via `POST /v1/chat/completions`. Mitigation: upgrade to `0.9.0` or later.
AI summary snake-internal / snake-material-v2
A vulnerability tracked as **CVE-2025-48944** has been found in vllm.
Attackers can target a specific entry point like `POST /v1/chat/completions` over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: ?/10.
What to do: upgrade vllm to **0.9.0** or later.
If unsure, ask your IT team or search "vllm CVE-2025-48944" on the vendor's site.
CVE-2025-48944 (vllm) — CWE-20 /
Attack vector: remote (network-reachable) / no user interaction
Attack surface: POST /v1/chat/completions
Patched: `0.9.0` — 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
**A vulnerability** (CWE-20) exists in vllm. Attackers reach the vulnerable code path via `POST /v1/chat/completions` without authentication.
📍 Affected scope
vllm — . Attack surface: POST /v1/chat/completions.
🔥 Severity
Severity: ?. Risk of unauthorized operations or information disclosure
🔧 How to fix
Update to **0.9.0**.
🛡️ 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 /v1/chat/completions` requests with malformed payloads or SQL meta-characters. Run `grep -r 'vllm' .` 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 'vllm' . | 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 `vllm` 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 /v1/chat/completions' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで `POST /v1/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 vllm to 0.9.0ステージング環境で 0.9.0 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 /v1/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
pip
vllm
[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.9.0"}]}]
PyPI
vllm
[{"type":"ECOSYSTEM","events":[{"introduced":"0.8.0"},{"fixed":"0.9.0"}]}]
References
- advisory https://nvd.nist.gov/vuln/detail/CVE-2025-48944
- advisory https://github.com/advisories/GHSA-vrq3-r879-7m65
- package https://github.com/vllm-project/vllm
- package https://pypi.org/project/vllm
- web https://github.com/vllm-project/vllm/security/advisories/GHSA-vrq3-r879-7m65
- web https://github.com/vllm-project/vllm/pull/17623
- web https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2023.yaml