Remote Code Execution Vulnerability in vLLM Multi-Node Cluster Configuration
Affected Environments
Note that this issue only affects the V0 engine, which has been off by default since v0.8.0. Further, the issue only applies to a deployment using tensor parallelism across multiple hosts, which we do not expect to be a common deployment pattern.
Since V0 is has been off by default since v0.8.0 and the fix is fairly invasive, we have decided not to fix this issue. Instead we recommend that users ensure their environment is on a secure network in case this pattern is in use.
The V1 engine is not affected by this issue.
Impact
In a multi-node vLLM deployment using the V0 engine, vLLM uses ZeroMQ for some multi-node communication purposes. The secondary vLLM hosts open a SUB ZeroMQ socket and connect to an XPUB socket on the primary vLLM host.
https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L295-L301
When data is received on this SUB socket, it is deserialized with pickle. This is unsafe, as it can be abused to execute code on a remote machine.
https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L468-L470
Since the vulnerability exists in a client that connects to the primary vLLM host, this vulnerability serves as an escalation point. If the primary vLLM host is compromised, this vulnerability could be used to compromise the rest of the hosts in the vLLM deployment.
Attackers could also use other means to exploit the vulnerability without requiring access to the primary vLLM host. One example would be the use of ARP cache poisoning to redirect traffic to a malicious endpoint used to deliver a payload with arbitrary code to execute on the target machine.
Data exposure via ZeroMQ on multi-node vLLM deployment
Impact
In a multi-node vLLM deployment, vLLM uses ZeroMQ for some multi-node communication purposes. The primary vLLM host opens an XPUB ZeroMQ socket and binds it to ALL interfaces. While the socket is always opened for a multi-node deployment, it is only used when doing tensor parallelism across multiple hosts.
Any client with network access to this host can connect to this XPUB socket unless its port is blocked by a firewall. Once connected, these arbitrary clients will receive all of the same data broadcasted to all of the secondary vLLM hosts. This data is internal vLLM state information that is not useful to an attacker.
By potentially connecting to this socket many times and not reading data published to them, an attacker can also cause a denial of service by slowing down or potentially blocking the publisher.
Detailed Analysis
The XPUB socket in question is created here:
https://github.com/vllm-project/vllm/blob/c21b99b91241409c2fdf9f3f8c542e8748b317be/vllm/distributed/device_communicators/shm_broadcast.py#L236-L237
Data is published over this socket via MessageQueue.enqueue() which is called by MessageQueue.broadcast_object():
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/device_communicators/shm_broadcast.py#L452-L453
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/device_communicators/shm_broadcast.py#L475-L478
The MessageQueue.broadcast_object() method is called by the GroupCoordinator.broadcast_object() method in parallel_state.py:
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/parallel_state.py#L364-L366
The broadcast over ZeroMQ is only done if the GroupCoordinator was created with use_message_queue_broadcaster set to True:
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/parallel_state.py#L216-L219
The only case where GroupCoordinator is created with use_message_queue_broadcaster is the coordinator for the tensor parallelism group:
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/parallel_state.py#L931-L936
To determine what data is broadcasted to the tensor parallism group, we must continue tracing. GroupCoordinator.broadcast_object() is called by GroupCoordinator.broadcoast_tensor_dict():
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/parallel_state.py#L489
which is called by broadcast_tensor_dict() in communication_op.py:
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/distributed/communication_op.py#L29-L34
If we look at _get_driver_input_and_broadcast() in the V0 worker_base.py, we'll see how this tensor dict is formed:
https://github.com/vllm-project/vllm/blob/790b79750b596043036b9fcbee885827fdd2ef3d/vllm/worker/worker_base.py#L332-L352
but the data actually sent over ZeroMQ is the metadata_list portion that is split from this tensor_dict. The tensor parts are sent via torch.distributed and only metadata about those tensors is sent via ZeroMQ.
https://github.com/vllm-project/vllm/blob/54a66e5fee4a1ea62f1e4c79a078b20668e408c6/vllm/distributed/parallel_state.py#L61-L83
Patches
https://github.com/vllm-project/vllm/pull/17197
Workarounds
Prior to the fix, your options include:
1. Do not expose the vLLM host to a network where any untrusted connections may reach the host.
2. Ensure that only the other vLLM hosts are able to connect to the TCP port used for the XPUB socket. Note that port used is random.
References
Relevant code first introduced in https://github.com/vllm-project/vllm/pull/6183
React Router allows pre-render data spoofing on React-Router framework mode
Summary
After some research, it turns out that it's possible to modify pre-rendered data by adding a header to the request. This allows to completely spoof its contents and modify all the values of the data object passed to the HTML. Latest versions are impacted.
Details
The vulnerable header is X-React-Router-Prerender-Data, a specific JSON object must be passed to it in order for the spoofing to be successful as we will see shortly. Here is the vulnerable code :
<img width="776" alt="Capture d’écran 2025-04-07 à 05 36 58" src="https://github.com/user-attachments/assets/c95b0b33-15ce-4d30-9f5e-b10525dd6ab4" />
To use the header, React-router must be used in Framework mode, and for the attack to be possible the target page must use a loader.
Steps to reproduce
Versions used for our PoC:
"@react-router/node": "^7.5.0",
"@react-router/serve": "^7.5.0",
"react": "^19.0.0"
"react-dom": "^19.0.0"
"react-router": "^7.5.0"
1. Install React-Router with its default configuration in Framework mode (https://reactrouter.com/start/framework/installation)
2. Add a simple page using a loader (example: routes/ssr)
3. Access your page (which uses the loader) by suffixing it with .data. In our case the page is called /ssr:
!image
We access it by adding the suffix .data and retrieve the data object, needed for the header:
!image
4. Send your request by adding the X-React-Router-Prerender-Data header with the previously retrieved object as its value. You can change any value of your data object (do not touch the other values, the latter being necessary for the object to be processed correctly and not throw an error):
!Capture d’écran 2025-04-07 à 05 56 10
As you can see, all values have been changed/overwritten by the values provided via the header.
Impact
The impact is significant, if a cache system is in place, it is possible to poison a response in which all of the data transmitted via a loader would be altered by an attacker allowing him to take control of the content of the page and modify it as he wishes via a cache-poisoning attack. This can lead to several types of attacks including potential stored XSS depending on the context in which the data is injected and/or how the data is used on the client-side.
Credits
Rachid Allam (zhero;)
Yasser Allam (inzo_)
React Router allows a DoS via cache poisoning by forcing SPA mode
Summary
After some research, it turns out that it is possible to force an application to switch to SPA mode by adding a header to the request. If the application uses SSR and is forced to switch to SPA, this causes an error that completely corrupts the page. If a cache system is in place, this allows the response containing the error to be cached, resulting in a cache poisoning that strongly impacts the availability of the application.
Details
The vulnerable header is X-React-Router-SPA-Mode; adding it to a request sent to a page/endpoint using a loader throws an error. Here is the vulnerable code :
<img width="672" alt="Capture d’écran 2025-04-07 à 08 28 20" src="https://github.com/user-attachments/assets/0a0e9c41-70fd-4dba-9061-892dd6797291" />
To use the header, React-router must be used in Framework mode, and for the attack to be possible the target page must use a loader.
Steps to reproduce
Versions used for our PoC:
"@react-router/node": "^7.5.0",
"@react-router/serve": "^7.5.0",
"react": "^19.0.0"
"react-dom": "^19.0.0"
"react-router": "^7.5.0"
1. Install React-Router with its default configuration in Framework mode (https://reactrouter.com/start/framework/installation)
2. Add a simple page using a loader (example: routes/ssr)
!image
3. Send a request to the endpoint using the loader (/ssr in our case) adding the following header:
``
X-React-Router-SPA-Mode: yes
``
Notice the difference between a request with and without the header;
Normal request
!Capture d’écran 2025-04-07 à 08 36 27
With the header
!Capture d’écran 2025-04-07 à 08 37 01
!image
Impact
If a system cache is in place, it is possible to poison the response by completely altering its content (by an error message), strongly impacting its availability, making the latter impractical via a cache-poisoning attack.
Credits
Rachid Allam (zhero;)
Yasser Allam (inzo_)
Gradio DOS in multipart boundry while uploading the file
A vulnerability in the file upload process of gradio-app/gradio version @gradio/video@0.10.2 allows for a Denial of Service (DoS) attack. An attacker can append a large number of characters to the end of a multipart boundary, causing the system to continuously process each character and issue warnings. This can render Gradio inaccessible for extended periods, disrupting services and causing significant downtime.
LlamaIndex vulnerable to Creation of Temporary File in Directory with Insecure Permissions
A vulnerability in the default_jsonalyzer function of the JSONalyzeQueryEngine in the run-llama/llama_index repository allows for SQL injection via prompt injection. This can lead to arbitrary file creation and Denial-of-Service (DoS) attacks. The vulnerability affects the latest version and is fixed in version 0.12.3.
Transformers Regular Expression Denial of Service (ReDoS) vulnerability
A Regular Expression Denial of Service (ReDoS) vulnerability was identified in the huggingface/transformers library, specifically in the file tokenization_nougat_fast.py. The vulnerability occurs in the post_process_single() function, where a regular expression processes specially crafted input. The issue stems from the regex exhibiting exponential time complexity under certain conditions, leading to excessive backtracking. This can result in significantly high CPU usage and potential application downtime, effectively creating a Denial of Service (DoS) scenario. The affected version is v4.46.3.
LlamaIndex Improper Handling of Exceptional Conditions vulnerability
A vulnerability in the LangChainLLM class of the run-llama/llama_index repository, version v0.12.5, allows for a Denial of Service (DoS) attack. The stream_complete method executes the llm using a thread and retrieves the result via the get_response_gen method of the StreamingGeneratorCallbackHandler class. If the thread terminates abnormally before the _llm.predict is executed, there is no exception handling for this case, leading to an infinite loop in the get_response_gen function. This can be triggered by providing an input of an incorrect type, causing the thread to terminate and the process to continue running indefinitely.
Gradio Vulnerable to Arbitrary File Deletion
A path traversal vulnerability exists in the Gradio Audio component of gradio-app/gradio, as of version git 98cbcae. This vulnerability allows an attacker to control the format of the audio file, leading to arbitrary file content deletion. By manipulating the output format, an attacker can reset any file to an empty file, causing a denial of service (DOS) on the server.
Gradio Vulnerable to Denial of Service (DoS) via Crafted HTTP Request
A Regular Expression Denial of Service (ReDoS) vulnerability exists in the gradio-app/gradio repository, affecting the gr.Datetime component. The affected version is git commit 98cbcae. The vulnerability arises from the use of a regular expression ^(?:\snow\s(?:-\s(\d+)\s([dmhs]))?)?\s*$ to process user input. In Python's default regex engine, this regular expression can take polynomial time to match certain crafted inputs. An attacker can exploit this by sending a crafted HTTP request, causing the gradio process to consume 100% CPU and potentially leading to a Denial of Service (DoS) condition on the server.
Gradio Vulnerable to Denial of Service (DoS) via Crafted Zip Bomb
A vulnerability in the dataframe component of gradio-app/gradio (version git 98cbcae) allows for a zip bomb attack. The component uses pd.read_csv to process input values, which can accept compressed files. An attacker can exploit this by uploading a maliciously crafted zip bomb, leading to a server crash and causing a denial of service.
vllm: Malicious model to RCE by torch.load in hf_model_weights_iterator
Description
The vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It use torch.load function and weights_only parameter is default value False. There is a security warning on https://pytorch.org/docs/stable/generated/torch.load.html, when torch.load load a malicious pickle data it will execute arbitrary code during unpickling.
Impact
This vulnerability can be exploited to execute arbitrary codes and OS commands in the victim machine who fetch the pretrained repo remotely.
Note that most models now use the safetensors format, which is not vulnerable to this issue.
References
https://pytorch.org/docs/stable/generated/torch.load.html
Fix: https://github.com/vllm-project/vllm/pull/12366
Deserialization of Untrusted Data in Hugging Face Transformers
Hugging Face Transformers Trax Model Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face Transformers. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file.
The specific flaw exists within the handling of model files. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-25012.
Deserialization of Untrusted Data in Hugging Face Transformers
Hugging Face Transformers MaskFormer Model Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face Transformers. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file.
The specific flaw exists within the parsing of model files. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-25191.
Deserialization of Untrusted Data in Hugging Face Transformers
Hugging Face Transformers MobileViTV2 Deserialization of Untrusted Data Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of Hugging Face Transformers. User interaction is required to exploit this vulnerability in that the target must visit a malicious page or open a malicious file.
The specific flaw exists within the handling of configuration files. The issue results from the lack of proper validation of user-supplied data, which can result in deserialization of untrusted data. An attacker can leverage this vulnerability to execute code in the context of the current user. Was ZDI-CAN-24322.
Starlette Denial of service (DoS) via multipart/form-data
Summary
Starlette treats multipart/form-data parts without a filename as text form fields and buffers those in byte strings with no size limit. This allows an attacker to upload arbitrary large form fields and cause Starlette to both slow down significantly due to excessive memory allocations and copy operations, and also consume more and more memory until the server starts swapping and grinds to a halt, or the OS terminates the server process with an OOM error. Uploading multiple such requests in parallel may be enough to render a service practically unusable, even if reasonable request size limits are enforced by a reverse proxy in front of Starlette.
PoC
``python
from starlette.applications import Starlette
from starlette.routing import Route
async def poc(request):
async with request.form():
pass
app = Starlette(routes=[
Route('/', poc, methods=["POST"]),
])
`
`sh
curl http://localhost:8000 -F 'big=</dev/urandom'
``
Impact
This Denial of service (DoS) vulnerability affects all applications built with Starlette (or FastAPI) accepting form requests.
Gradio uses insecure communication between the FRP client and server
Impact
What kind of vulnerability is it? Who is impacted?
This vulnerability involves insecure communication between the FRP (Fast Reverse Proxy) client and server when Gradio's share=True option is used. HTTPS is not enforced on the connection, allowing attackers to intercept and read files uploaded to the Gradio server, as well as modify responses or data sent between the client and server. This impacts users who are sharing Gradio demos publicly over the internet using share=True without proper encryption, exposing sensitive data to potential eavesdroppers.
Patches
Yes, please upgrade to gradio>=5 to address this issue.
Workarounds
Is there a way for users to fix or remediate the vulnerability without upgrading?
As a workaround, users can avoid using share=True in production environments and instead host their Gradio applications on servers with HTTPS enabled to ensure secure communication.
Gradio has a race condition in update_root_in_config may redirect user traffic
Impact
What kind of vulnerability is it? Who is impacted?
This vulnerability involves a race condition in the update_root_in_config function, allowing an attacker to modify the root URL used by the Gradio frontend to communicate with the backend. By exploiting this flaw, an attacker can redirect user traffic to a malicious server. This could lead to the interception of sensitive data such as authentication credentials or uploaded files. This impacts all users who connect to a Gradio server, especially those exposed to the internet, where malicious actors could exploit this race condition.
Patches
Yes, please upgrade to gradio>=5 to address this issue.
Gradio lacks integrity checking on the downloaded FRP client
Impact
This vulnerability is a lack of integrity check on the downloaded FRP client, which could potentially allow attackers to introduce malicious code. If an attacker gains access to the remote URL from which the FRP client is downloaded, they could modify the binary without detection, as the Gradio server does not verify the file's checksum or signature.
Who is impacted?
Any users utilizing the Gradio server's sharing mechanism that downloads the FRP client could be affected by this vulnerability, especially those relying on the executable binary for secure data tunneling.
Patches
Yes, please upgrade to gradio>=5.0, which includes a fix to verify the integrity of the downloaded binary.
Workarounds
There is no direct workaround for this issue without upgrading. However, users can manually validate the integrity of the downloaded FRP client by implementing checksum or signature verification in their own environment to ensure the binary hasn't been tampered with.
Gradios's CORS origin validation is not performed when the request has a cookie
Impact
What kind of vulnerability is it? Who is impacted?
This vulnerability is related to CORS origin validation, where the Gradio server fails to validate the request origin when a cookie is present. This allows an attacker’s website to make unauthorized requests to a local Gradio server. Potentially, attackers can upload files, steal authentication tokens, and access user data if the victim visits a malicious website while logged into Gradio. This impacts users who have deployed Gradio locally and use basic authentication.
Patches
Yes, please upgrade to gradio>=4.44 to address this issue.
Workarounds
Is there a way for users to fix or remediate the vulnerability without upgrading?
As a workaround, users can manually enforce stricter CORS origin validation by modifying the CustomCORSMiddleware class in their local Gradio server code. Specifically, they can bypass the condition that skips CORS validation for requests containing cookies to prevent potential exploitation.
OWASP A01OWASP A05LLM06 · Sensitive Info DisclosureOWASP LLM
Get guardrail →