Vulnerability in vllm (CVE-2026-44222)
Summary
Vulnerability in vllm (CVE-2026-44222). Risk of unauthorized operations or information disclosure. Exploitable via image_grid_thw. Mitigation: upgrade to 0.20.0 or later.
Original description
The description as published by the source.
vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.
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-2026-44222 has been found in vllm.
Attackers can target a specific entry point like image_grid_thw over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: upgrade vllm to 0.20.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-44222" on the vendor's site.
CVE-2026-44222 (vllm) — CWE-129 / CVSS v3 6.5
Attack vector: remote (network-reachable) / no user interaction
Attack surface: image_grid_thw / video_grid_thw
Patched: 0.20.0 — 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.
A vulnerability (CWE-129) exists in vllm. Attackers reach the vulnerable code path via image_grid_thw.
Check the vendor advisory for the affected versions of vllm. Attack surface: image_grid_thw / video_grid_thw.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to 0.20.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. 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。 -
2Apply patch patch
Upgrade vllm to 0.20.0ステージング環境で 0.20.0 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を含めること。
-
3Post-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
- report github.com
- web github.com
- web github.com
- web github.com
- web pypi.org