Vulnerability in vllm (CVE-2026-22778)
Summary
Vulnerability in vllm (CVE-2026-22778). Successful exploitation can lead to full system takeover. Exploitable via POST /v1/chat/completions. Mitigation: upgrade to 0.14.1 or later.
Original description
The description as published by the source.
vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
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-2026-22778 has been found in vllm.
Attackers can target a specific entry point like POST /v1/chat/completions over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 9.8/10.
What to do: upgrade vllm to 0.14.1 or later.
If unsure, ask your IT team or search "vllm CVE-2026-22778" on the vendor's site.
CVE-2026-22778 (vllm) — CWE-122 / CVSS v3 9.8
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Attack surface: POST /v1/chat/completions / POST /v1/invocations / cdef / video_url
Patched: 0.14.1 — 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.
A vulnerability (CWE-122) exists in vllm. Attackers reach the vulnerable code path via POST /v1/chat/completions without authentication.
Check the vendor advisory for the affected versions of vllm. Attack surface: POST /v1/chat/completions / POST /v1/invocations / cdef / video_url.
Severity: Critical (CVSS 9.8/10). Successful exploitation can lead to full system takeover.
Update to 0.14.1.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
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
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。 -
2Hunt 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。 -
3Apply patch patch
Upgrade vllm to 0.14.1ステージング環境で 0.14.1 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 2 で見つけた異常検知の続報チェックを含めること。
-
4Post-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 2 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
References
- advisory github.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory nvd.nist.gov
- advisory github.com
- advisory github.com
- package pypi.org
- package github.com
- patch github.com
- patch github.com
- report bugzilla.redhat.com
- web github.com
- web security.access.redhat.com
- web github.com