Code Injection in vllm (CVE-2026-41523)
Summary
Code injection in vllm (CVE-2026-41523). Successful exploitation can lead to full system takeover. Exploitable via assert. Mitigation: upgrade to 0.22.0 or later.
Original description
The description as published by the source.
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
Source: GitHub Security Advisories (Global) 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-2026-41523 has been found in vllm.
Attackers can target a specific entry point like assert over the network to misuse the product.
Successful exploitation can lead to full system takeover. CVSS score: 7.5/10.
What to do: upgrade vllm to 0.22.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-41523" on the vendor's site.
CVE-2026-41523 (vllm) — CWE-94 / CVSS v3 7.5
Attack vector: remote (network-reachable) / unauthenticated
Attack surface: assert / function_name / resolve_obj_by_qualname
Patched: 0.22.0 — 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.
Arbitrary code execution (CWE-94) exists in vllm. Attackers reach the vulnerable code path via assert without authentication.
Check the vendor advisory for the affected versions of vllm. Attack surface: assert / function_name / resolve_obj_by_qualname.
Severity: High (CVSS 7.5/10). Successful exploitation can lead to full system takeover.
Update to 0.22.0.
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 0.22.0ステージング環境で 0.22.0 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 access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory nvd.nist.gov
- 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 access.redhat.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory github.com
- patch github.com
- report bugzilla.redhat.com
- web huntr.com
- web github.com
- web security.access.redhat.com
- web github.com