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.
PUBLISHED5.2CWE-918
SSRF Protection Bypass in vLLM
Problem type
Affected products
vllm-project
vllm
>= 0.15.1, < 0.17.0 - AFFECTED
References
https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536
https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536
https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
https://github.com/vllm-project/vllm/pull/34743
https://github.com/vllm-project/vllm/pull/34743
https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0
https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0
GitHub Security Advisories
GHSA-v359-jj2v-j536
vLLM has SSRF Protection Bypass
https://github.com/advisories/GHSA-v359-jj2v-j536Summary
The SSRF protection fix for https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc 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.
Affected Component
- File:
vllm/connections.py - Function:
load_from_url_async
Vulnerability Details
Root Cause
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.
These two URL parsers handle backslash characters (\) differently:
urllib3.parse_url()
https://httpbin.org\@evil.com/
httpbin.org
/%5C@evil.com/
URL-encodes \ as %5C, treats \@evil.com/ as part of the path
yarl (via aiohttp)
https://httpbin.org\@evil.com/
evil.com
/
Treats \ as part of userinfo (user: httpbin.org\), the @ acts as the userinfo/host separator
Attack Scenario
# Attacker provides this URL
malicious_url = "https://httpbin.org\\@evil.com/"
# 1. Validation layer (urllib3.parse_url)
parsed = urllib3.util.parse_url(malicious_url)
# parsed.host == "httpbin.org" ✅ Passes validation
# 2. Actual request (aiohttp with yarl)
async with aiohttp.ClientSession() as session:
async with session.get(malicious_url) as response:
# Request actually goes to evil.com! ❌ Bypass!
Why This Happens
- yarl: Interprets
httpbin.org\as the userinfo component, and@as the userinfo/host separator, so the URL is parsed asuser=httpbin.org\,host=evil.com,path=/ - urllib3: URL-encodes the backslash as
%5C, so\@evil.com/becomes/%5C@evil.com/which is treated as part of the path, leavinghost=httpbin.org
This inconsistency allows an attacker to:
- Bypass the hostname allowlist check
- Access arbitrary internal/external services
- Perform full SSRF attacks
Fixes
github.com
https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc
github.com
https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536
github.com
https://github.com/vllm-project/vllm/pull/34743
github.com
https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0
github.com
https://github.com/advisories/GHSA-v359-jj2v-j536
JSON source
https://cveawg.mitre.org/api/cve/CVE-2026-25960Click to expand
{
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"cveMetadata": {
"cveId": "CVE-2026-25960",
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"dateUpdated": "2026-03-09T21:01:01.827Z",
"dateReserved": "2026-02-09T17:13:54.066Z",
"datePublished": "2026-03-09T21:01:01.827Z",
"state": "PUBLISHED"
},
"containers": {
"cna": {
"providerMetadata": {
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M",
"dateUpdated": "2026-03-09T21:01:01.827Z"
},
"title": "SSRF Protection Bypass in vLLM",
"descriptions": [
{
"lang": "en",
"value": "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."
}
],
"affected": [
{
"vendor": "vllm-project",
"product": "vllm",
"versions": [
{
"version": ">= 0.15.1, < 0.17.0",
"status": "affected"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"lang": "en",
"description": "CWE-918: Server-Side Request Forgery (SSRF)",
"cweId": "CWE-918",
"type": "CWE"
}
]
}
],
"references": [
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536",
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-v359-jj2v-j536",
"tags": [
"x_refsource_CONFIRM"
]
},
{
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc",
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-qh4c-xf7m-gxfc",
"tags": [
"x_refsource_MISC"
]
},
{
"url": "https://github.com/vllm-project/vllm/pull/34743",
"name": "https://github.com/vllm-project/vllm/pull/34743",
"tags": [
"x_refsource_MISC"
]
},
{
"url": "https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0",
"name": "https://github.com/vllm-project/vllm/commit/6f3b2047abd4a748e3db4a68543f8221358002c0",
"tags": [
"x_refsource_MISC"
]
}
],
"metrics": [
{
"cvssV3_1": {
"version": "3.1",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:L",
"attackVector": "NETWORK",
"attackComplexity": "LOW",
"privilegesRequired": "LOW",
"userInteraction": "NONE",
"scope": "UNCHANGED",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"availabilityImpact": "LOW",
"baseScore": 7.1,
"baseSeverity": "HIGH"
}
}
]
}
}
}