Read the docs
TI-2026-20985 Aliases CVE-2026-25960GHSA-v359-jj2v-j536

SSRF Protection Bypass in vLLM

Priority MEDIUM 43CWE-918Published · Updated

Key facts

Attack vector
Network
Privileges required
None
User interaction
None
Attack complexity
Low
Impact type
—
Confidentiality · integrity · availability
High · High · High
Fix status
Partial Red Hat: 1 fixed, 3 without a fix

Attack profile from CVSS 3.1 · NVD. Fix status from CNA, GitHub and Red Hat.

Summary

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.

Why it matters now

Exploitation None reported CISA SSVC · not in CISA KEV
EPSS 0.00605 49th percentileScored 2026-11-07
Public exploit Yes 1 exploit referenceTagged by NVD
Fix Partial vllm (vllm-project): 0.17.0vllm (PyPI): 0.17.0Red Hat: 3 advisoriesRed Hat: 1 fixed, 3 without a fix

SSVC decision points

CISA ADP · SSVC 2.0.3

Exploitation
None
Automatable
No
Technical impact
Partial

The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.

Affected products

VendorProductAffected versionsFixed inStatusSource
vllm-projectvllm0.15.1 to before 0.17.00.17.0Patch availableCNA
—vllm (PyPI)0.15.1 to before 0.17.00.17.0Patch availableGHSA-v359-jj2v-j536
  • vllm Vendorvllm-project Affected 0.15.1 to before 0.17.0 Fixed in 0.17.0 Patch available CNA
  • vllm (PyPI) Vendor— Affected 0.15.1 to before 0.17.0 Fixed in 0.17.0 Patch available GHSA-v359-jj2v-j536

CPE configurations NVD · 1

CPEVersionsRoleVendor
cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*0.15.1 to before 0.17.0VulnerablevLLM
  • cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* Versions 0.15.1 to before 0.17.0 Vulnerable ·vLLM

Remediation

  • Fix · CNA vllm (vllm-project) Fixed in 0.17.0
  • Fix · GHSA-v359-jj2v-j536 vllm (PyPI) Fixed in 0.17.0 Advisory →

Red Hat 3 advisories

  • RHSA-2026:87410 Released 2026-10-21 · Red Hat rating Critical
    RHOAI 2.25.12 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-built-in-detector-rhel9, registry.redhat.io/rhoai/odh-caikit-nlp-rhel9, registry.redhat.io/rhoai/odh-codeflare-operator-rhel9 +47
  • RHSA-2026:42644 Released 2026-07-21 · Red Hat rating Important
    RHOAI 2.25.9 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-feature-server-rhel9, registry.redhat.io/rhoai/odh-kserve-storage-initializer-rhel9 +36
  • RHSA-2026:24977 Released 2026-06-10 · Red Hat rating Important
    RHOAI 2.25.7 - Red Hat OpenShift AI
    • Red Hat OpenShift AI 2.25 registry.redhat.io/rhoai/odh-caikit-nlp-rhel9, registry.redhat.io/rhoai/odh-caikit-tgis-serving-rhel9, registry.redhat.io/rhoai/odh-dashboard-rhel9 +34

Vendor assessments

Red Hat

Red Hat rating: Important. Red Hat's page for this CVE →

ProductStatusPlan or fix
Red Hat AI Inference ServerAffectedNo fix yet
Red Hat Enterprise Linux AI (RHEL AI) 3AffectedNo fix planned: Will not fix
Red Hat OpenShift AI (RHOAI)AffectedNo fix planned: Out of support scope
Red Hat OpenShift AI 2.25Fixed RHSA-2026:24977, RHSA-2026:42644, RHSA-2026:87410
Not affected: 2 products
  • Red Hat OpenShift AI (RHOAI)
  • Red Hat OpenShift AI 2.25

Timeline

  1. 2026-10-02 Threatist record created from CVE-2026-25960
  2. 2026-10-03 Alias added: GHSA-v359-jj2v-j536
  3. 2026-10-22 Fix available: RHSA-2026:87410 · Red Hat
  4. 2026-10-23 Affected versions changed · Red Hat
  5. 2026-10-25 EPSS moved to the below the 50th percentile
  6. 2026-11-06 Fix available: RHSA-2026:42644 · Red Hat

References

Exploit 1

Patch 2

Advisory 2

Other 8

  • TI-2024-10229 Remote Code Execution in vllm-project/vllm CVSS 3.0CRITICAL 9.8
  • TI-2024-08404 Remote Code Execution in vllm-project/vllm CVSS 3.1CRITICAL 9.8
  • TI-2026-36017 vLLM: OpenAI auth bypass CVSS 3.1CRITICAL 9.1
  • TI-2026-63056 vLLM before 0.28.0 Denial of Service via negative token ID CVSS 4.0HIGH 8.7
  • TI-2026-04308 Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control CVSS 3.0HIGH 8.8
  • TI-2026-39137 vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection CVSS 3.1HIGH 7.5
See all 124 →

Sources

This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences