Skip to content

GHSA-vvpg-rrww-wpmh CVE-2026-115917 PYSEC-2026-4348

vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server

Medium PyPI
Severity
3.4 / 10
Medium · CVSS 3.1
Exploit chance (EPSS)
0.24%
Chance of exploitation in the next 30 days. Higher than 15.21% of scored vulnerabilities.
Known exploited
No
Not in CISA's catalog
Weakness
CWE-942 Permissive Cross-domain Security Policy with Untrusted Domains
Fix
0.32.0
Upgrade vllm to this version or later

Description

Summary

The OpenAI-compatible server registers Starlette CORSMiddleware with allowed_origins defaulting to ["*"], and performs no authentication unless --api-key (or VLLM_API_KEY) is configured. A web page on any origin can send requests to a vLLM server that the victim's browser can reach (for example localhost or an internal/VPN address) and read the responses. The default allow_credentials=False blocks cookie-bearing cross-origin requests; because vLLM authenticates with a bearer header rather than cookies, the wildcard still permits untokenized access to an unauthenticated server and read access when the caller already holds a token.

Details

Affected components

  • vllm/entrypoints/launchers/cli_args.py - allowed_origins default value.
  • vllm/entrypoints/serve/middleware/register.py - CORSMiddleware registration.
  • vllm/entrypoints/serve/middleware/authenticate.py - auth middleware and its guarded path prefixes.

Root cause

vllm/entrypoints/launchers/cli_args.py:

allow_credentials: bool = False
"""Allow credentials."""
allowed_origins: list[str] = field(default_factory=lambda: ["*"])
"""Allowed origins."""

vllm/entrypoints/serve/middleware/register.py:

app.add_middleware(
    CORSMiddleware,
    allow_origins=args.allowed_origins,
    allow_credentials=args.allow_credentials,
    allow_methods=args.allowed_methods,
    allow_headers=args.allowed_headers,
)

The auth middleware is added only when a token is configured and guards only the /v1, /v2, /inference, and /cohere prefixes. /v1/load_lora_adapter and /v1/unload_lora_adapter are inside /v1 and therefore do require a key when one is set; they are open only when no key is configured and dynamic LoRA updating is enabled.

Impact

  • A malicious page can enumerate models (GET /v1/models), issue POST /v1/chat/completions, consume GPU time, and read model output through the victim's browser.
  • When the server is reachable only from the victim's network, the browser acts as a proxy a remote website could not otherwise use.
  • With allow_credentials=False, cookie-based CSRF does not apply; the exposure is cross-origin request execution and response disclosure.

This advisory was fixed in MR61009.

Affected versions

PyPI

PackageVulnerableFixed in
vllm
< 0.32.0
0.32.0
vllm
< 0.32.0
0.32.0

How to fix

Move to the fixed version or later with your package manager, update the lockfile, and run your tests. If the package only arrives through another dependency, upgrade that dependency first. If none of its releases pulls a fixed version yet, force the version with your package manager's override.

vllm PyPI → 0.32.0

pip
pip install --upgrade "vllm>=0.32.0"
poetry
poetry add "vllm>=0.32.0"
uv
uv add "vllm>=0.32.0"

Severity breakdown

CVSS 3.1 3.4

CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:C/C:L/I:N/A:N

Attack vector
Network
Attack complexity
High
Privileges required
None
User interaction
Required
Scope
Changed
Confidentiality
Low
Integrity
None
Availability
None

Weakness

CWE-942: Permissive Cross-domain Security Policy with Untrusted Domains

The product uses a web-client protection mechanism such as a Content Security Policy (CSP) or cross-domain policy file, but the policy includes untrusted domains with which the web client is allowed to communicate.

How to prevent it
  • Architecture and Design, Operation: Define a restrictive Content Security Policy [REF-1486] or cross-domain policy file.
  • Architecture and Design, Operation: Avoid using wildcards in the CSP / cross-domain policy file. Any domain matching the wildcard expression will be implicitly trusted, and can perform two-way interaction with the target server.
  • Architecture and Design, Operation: For Flash, modify crossdomain.xml to use meta-policy options such as 'master-only' or 'none' to reduce the possibility of an attacker planting extraneous cross-domain policy files on a server.

References

Timeline

  1. Published
  2. Last updated by the source
  3. Latest EPSS score
AdvisorySeverityWhy it's related
GHSA-8397-8qf6-f2gm
vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine
Medium Also affects vllm
GHSA-x567-49g5-p4cf
vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs
Medium Also affects vllm
GHSA-q97c-p368-75c4
vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
Medium Also affects vllm
GHSA-h3rc-j82p-2c3h
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
High Also affects vllm
GHSA-gq5q-89c7-vhvx
vLLM DeepSeek-OCR image processing vulnerable to denial of service
Medium Also affects vllm
GHSA-6757-hggm-hp2w
vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled
High Also affects vllm
GHSA-542m-9234-8gvf
vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool
Medium Also affects vllm
PYSEC-2026-4353
vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal…
High Also affects vllm

Credits: jperezdealgaba, prnjlksingh

Is this in your code?

MergeHarbor checks every repository's dependencies against this database, ranks what matters by exploitability and reachability, routes it to the owning team and opens the fix pull request.

Check your repos with MergeHarbor