SSRF (Server-Side Request Forgery) in vllm (CVE-2026-25960)
Summary
SSRF in vllm (CVE-2026-25960). Risk of unauthorized operations or information disclosure. Exploitable via load_from_url_async. Mitigation: upgrade to 0.17.0 or later.
Original description
The description as published by the source.
vLLM is an inference and serving engine for large language models (LLMs). The SSRF protection fix for CVE-2026-24779 add in 0.15.1 can be bypassed in the load_from_url_async method due to inconsistent URL parsing behavior between the validation layer and the actual HTTP client. The SSRF fix uses urllib3.util.parse_url() to validate and extract the hostname from user-provided URLs. However, load_from_url_async uses aiohttp for making the actual HTTP requests, and aiohttp internally uses the yarl library for URL parsing. This vulnerability in 0.17.0.
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-2026-25960 has been found in vllm.
Attackers can target a specific entry point like load_from_url_async over the network to misuse the product.
Risk of unauthorized operations or information disclosure. CVSS score: 7.1/10.
What to do: upgrade vllm to 0.17.0 or later.
If unsure, ask your IT team or search "vllm CVE-2026-25960" on the vendor's site.
CVE-2026-25960 (vllm) — CWE-918 / CVSS v3 7.1
Attack vector: remote (network-reachable) / no user interaction
Attack surface: load_from_url_async / aiohttp / yarl / httpbin.org
Patched: 0.17.0 — 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.
SSRF (CWE-918) exists in vllm. Attackers reach the vulnerable code path via load_from_url_async.
Check the vendor advisory for the affected versions of vllm. Attack surface: load_from_url_async / aiohttp / yarl / httpbin.org.
Severity: High (CVSS 7.1/10). Risk of unauthorized operations or information disclosure.
Update to 0.17.0.
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 0.17.0ステージング環境で 0.17.0 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 github.com
- advisory access.redhat.com
- advisory access.redhat.com
- advisory nvd.nist.gov
- advisory github.com
- advisory access.redhat.com
- advisory github.com
- package github.com
- patch github.com
- patch github.com
- report bugzilla.redhat.com
- web security.access.redhat.com
- web github.com
- web pypi.org