vllm
Affected
- introduced
0.16.0, fixed0.19.0(ecosystem)
Fixed versions
0.19.0
Fix
- Fixed version
0.19.0pip install --upgrade vllm==0.19.0
Advisory
Also known as: CVE-2026-34753, GHSA-pf3h-qjgv-vcpr
vLLM: Server-Side Request Forgery (SSRF) in download_bytes_from_url
Summary
A Server Side Request Forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions.
This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host.
------
Details
Vulnerable component
The vulnerable logic is in the batch runner entrypoint vllm/entrypoints/openai/run_batch.py, function download_bytes_from_url:
# run_batch.py Lines 442-482
async def download_bytes_from_url(url: str) -> bytes:
"""
Download data from a URL or decode from a data URL.
Args:
url: Either an HTTP/HTTPS URL or a data URL (data:...;base64,...)
Returns:
Data as bytes
"""
parsed = urlparse(url)
# Handle data URLs (base64 encoded)
if parsed.scheme == "data":
# Format: data:...;base64,<base64_data>
if "," in url:
header, data = url.split(",", 1)
if "base64" in header:
return base64.b64decode(data)
else:
raise ValueError(f"Unsupported data URL encoding: {header}")
else:
raise ValueError(f"Invalid data URL format: {url}")
# Handle HTTP/HTTPS URLs
elif parsed.scheme in ("http", "https"):
async with (
aiohttp.ClientSession() as session,
session.get(url) as resp,
):
if resp.status != 200:
raise Exception(
f"Failed to download data from URL: {url}. Status: {resp.status}"
)
return await resp.read()
else:
raise ValueError(
f"Unsupported URL scheme: {parsed.scheme}. "
"Supported schemes: http, https, data"
)
Key properties:
data, http, https).http / https, it directly calls session.get(url) on the provided string.MediaConnector), which implements an explicit domain allowlist. download_bytes_from_url does not reuse that protection.URL controllability
The url argument is fully controlled by batch input JSON via the file_url field of BatchTranscriptionRequest / BatchTranslationRequest.
# run_batch.py Line 67-80
class BatchTranscriptionRequest(TranscriptionRequest):
"""
Batch transcription request that uses file_url instead of file.
This class extends TranscriptionRequest but replaces the file field
with file_url to support batch processing from audio files written in JSON format.
"""
file_url: str = Field(
...,
description=(
"Either a URL of the audio or a data URL with base64 encoded audio data. "
),
)
# run_batch.py Line 98-111
class BatchTranslationRequest(TranslationRequest):
"""
Batch translation request that uses file_url instead of file.
This class extends TranslationRequest but replaces the file field
with file_url to support batch processing from audio files written in JSON format.
"""
file_url: str = Field(
...,
description=(
"Either a URL of the audio or a data URL with base64 encoded audio data. "
),
)
There is no restriction on the domain, IP, or port of file_url in these models.
# run_batch.py Line 139-179
class BatchRequestInput(OpenAIBaseModel):
...
url: str
body: BatchRequestInputBody
@field_validator("body", mode="plain")
@classmethod
def check_type_for_url(cls, value: Any, info: ValidationInfo):
url: str = info.data["url"]
...
if url == "/v1/audio/transcriptions":
return BatchTranscriptionRequest.model_validate(value)
if url == "/v1/audio/translations":
return BatchTranslationRequest.model_validate(value)
# run_batch.py Line 770-781
logger.info("Reading batch from %s...", args.input_file)
# Submit all requests in the file to the engine "concurrently".
response_futures: list[Awaitable[BatchRequestOutput]] = []
for request_json in (await read_file(args.input_file)).strip().split("\n"):
# Skip empty lines.
request_json = request_json.strip()
if not request_json:
continue
request = BatchRequestInput.model_validate_json(request_json)
The batch runner reads each line of the input file (args.input_file), parses it as JSON, and constructs a BatchTranscriptionRequest / BatchTranslationRequest. Whatever file_url appears in that JSON line becomes batch_request_body.file_url.
file_url is passed directly into download_bytes_from_url:# run_batch.py Line 610-623
def wrapper(handler_fn: Callable):
async def transcription_wrapper(
batch_request_body: (BatchTranscriptionRequest | BatchTranslationRequest),
) -> (
TranscriptionResponse
| TranscriptionResponseVerbose
| TranslationResponse
| TranslationResponseVerbose
| ErrorResponse
):
try:
# Download data from URL
audio_data = await download_bytes_from_url(batch_request_body.file_url)
So the data flow is:
body.file_url.BatchRequestInput / BatchTranscriptionRequest / BatchTranslationRequest parse that JSON and store file_url verbatim.make_transcription_wrapper calls download_bytes_from_url(batch_request_body.file_url).download_bytes_from_url’s HTTP/HTTPS branch issues aiohttp.ClientSession().get(url) to that attacker-controlled URL with no further validation.This is a classic SSRF pattern: a server-side component makes arbitrary HTTP requests to a URL string taken from untrusted input.
Comparison with safer code
The project already contains a safer URL-handling path for multimodal media in vllm/multimodal/media/connector.py, which demonstrates the intent to mitigate SSRF via domain allowlists and URL normalization:
# connector.py Lines 169-189
def load_from_url(
self,
url: str,
media_io: MediaIO[_M],
*,
fetch_timeout: int | None = None,
) -> _M: # type: ignore[type-var]
url_spec = parse_url(url)
if url_spec.scheme and url_spec.scheme.startswith("http"):
self._assert_url_in_allowed_media_domains(url_spec)
connection = self.connection
data = connection.get_bytes(
url_spec.url,
timeout=fetch_timeout,
allow_redirects=envs.VLLM_MEDIA_URL_ALLOW_REDIRECTS,
)
return media_io.load_bytes(data)Medium Basis: CVSS v3 score 5.4, vector CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
0.16.0, fixed 0.19.0 (ecosystem)0.19.0
0.19.0pip install --upgrade vllm==0.19.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: PyPA Advisory Database · CC BY 4.0