CVE-2026-25960
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedvLLM 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.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceThis is an SSRF bypass vulnerability in vLLM's load_from_url_async method. The fix for CVE-2026-24779 used urllib3.util.parse_url() to validate URLs, but the actual HTTP requests are made using aiohttp which internally uses the yarl library for URL parsing. Due to inconsistent URL parsing behavior between these two libraries, specially crafted URLs can pass validation but be interpreted differently by aiohttp, allowing attackers to access internal services that should be protected by SSRF controls.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data>= 0.15.1, < 0.17.0CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Check installed vLLM versionRun `pip show vllm` or `pip list | grep vllm` to see the installed version numberAffected if The version is >= 0.15.1 and < 0.17.0 (including any 0.16.x release)
-
Identify usage of load_from_url_asyncSearch codebase or configuration files for references to `load_from_url_async` method, particularly in model loading or data loading contextsAffected if The method is actively used or exposed in the deployment configuration
-
Verify URL-based model loading is enabledInspect configuration files (e.g., config.yaml, environment variables) for settings that enable loading models or data from HTTP/HTTPS URLsAffected if URL-based loading is enabled and the service can accept external URLs for model or data input
-
Check network exposure of the vLLM serviceReview network configuration to determine if the vLLM service has access to internal network resources or if there are firewall/network policies restricting outbound connectionsAffected if The service can make outbound HTTP connections to internal network targets (e.g., internal APIs, metadata services, intranet resources)
You are affected if vLLM version is 0.15.1 through 0.16.x AND the load_from_url_async functionality is in use, allowing potentially malicious URLs to bypass SSRF protection and access internal resources.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped0.17.0
Until an official patch is released, avoid using load_from_url_async with untrusted user-provided URLs. Consider implementing additional network-level controls to restrict outbound connections from the inference server.
vLLM 0.17.0
- Upgrade vLLM to version 0.17.0 or later to resolve the SSRF vulnerability
- Verify the upgrade by checking the vLLM version with: `vllm --version`
- Ensure any custom URL loading configurations are tested after upgrade
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation4.0 h
- Implementation12.0 h
- Testing6.0 h
- Review / QA3.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $7,040.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-25960 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-25960 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data