Vulnerability in vllm (CVE-2026-105754)
Summary
Vulnerability in vllm (CVE-2026-105754). Risk of unauthorized operations or information disclosure. Exploitable via POST /v1/chat/completions/render. Mitigation: upgrade to 0.30.0 or later.
Original description
The description as published by the source.
Affected
- Ecosystem / package: pip /
vllm - Affected versions: vLLM ≤ 0.25.1 (confirmed on 0.25.1, commit
752a3a504485). The lower bound predates 0.25.1; maintainers can confirm how far back the scale-out transport path reaches.
Summary
vLLM's disaggregated scale-out transport splits a multimodal request into a trusted render step (POST /v1/chat/completions/render) and a separate generate step (POST /inference/v1/generate). The generate route decodes a caller-supplied features object — serialized encoder tensors (kwargs_data), multimodal hashes (mm_hashes), placeholder ranges (mm_placeholders), and the internal field-processor selection — and forwards it into the engine as if it had come from the trusted renderer, with no rebinding to (or validation against) the active model's renderer contract. Because the two routes are ordinary auth-guarded HTTP endpoints (the /inference prefix is registered by default on generate-capable servers), any authenticated caller can submit an otherwise-valid render body with a single forged field.
Depending on which field is forged, this produces:
- an engine-fatal crash of the shared EngineCore process (denial of service), reproduced as a CUDA illegal-memory-access, a post-admission rank-mismatch
ValueError, and a hardassert— three independent forged fields (sites 1, 2, 3); - **silent cross-request encode…
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-2026-105754 has been found in vllm.
Attackers can target a specific entry point like POST /v1/chat/completions/render 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 0.30.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-105754" on the vendor's site.
CVE-2026-105754 (vllm) — CWE-20 / CVSS v3 6.5
Attack vector: remote (network-reachable) / no user interaction
Attack surface: POST /v1/chat/completions/render / POST /inference/v1/generate / vllm / features
Patched: 0.30.0 — 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-20) exists in vllm. Attackers reach the vulnerable code path via POST /v1/chat/completions/render.
Check the vendor advisory for the affected versions of vllm. Attack surface: POST /v1/chat/completions/render / POST /inference/v1/generate / vllm / features.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to 0.30.0.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual POST /v1/chat/completions/render 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/render' /var/log/nginx/access.log | grep -E '(unusual_payload|sqli_pattern)'アクセスログで
POST /v1/chat/completions/render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 0.30.0ステージング環境で 0.30.0 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 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/render 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。