CVE-2026-34753

# 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"
        )

# 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. "
        ),
    )

# 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)

# 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)

# 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)

# connector.py Lines 158-167
  def _assert_url_in_allowed_media_domains(self, url_spec: Url) -> None:
        if (
            self.allowed_media_domains
            and url_spec.hostname not in self.allowed_media_domains
        ):
            raise ValueError(
                f"The URL must be from one of the allowed domains: "
                f"{self.allowed_media_domains}. Input URL domain: "
                f"{url_spec.hostname}"
            )