GitHub Advisoryadvisory · PyPI

GHSA-v359-jj2v-j536 vLLM has SSRF Protection Bypass

MEDIUM Published 2026-03-09 Modified 2026-07-17 Official page ↗
Aliases
CVE-2026-25960
Ecosystem
PyPI
Packages
vllm
Severity
Moderate
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
Weaknesses
CWE-918
Reviewed
2026-03-09

Affected packages

• PyPI vllm: >= 0.15.1, < 0.17.0 → fixed in 0.17.0

Description

Summary 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: | Parser | Input URL | Parsed Host | Parsed Path | Behavior | |--------|-----------|-------------|-------------|----------| | `urllib3.parse_url()` | `https://httpbin.org\@evil.com/` | `httpbin.org` | `/%[email protected]/` | 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 ```python 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 1. yarl: Interprets `httpbin.org\` as the userinfo component, and `@` as the userinfo/host separator, so the URL is parsed as `user=httpbin.org\`, `host=evil.com`, `path=/` 2. urllib3: URL-encodes the backslash as `%5C`, so `\@evil.com/` becomes `/%[email protected]/` which is treated as part of the path, leaving `host=httpbin.org` This inconsistency allows an attacker to: • Bypass the hostname allowlist check • Access arbitrary internal/external services • Perform full SSRF attacks Fixes • https://github.com/vllm-project/vllm/pull/34743

Related

Alias · CVE (1)

  • CVE-2026-25960 vLLM is an inference and serving engine for large language models (LLMs). vulnerability

Weakness · CWE (1)

  • CWE-918 Server-Side Request Forgery weakness

References