1405 matches found
CVE-2026-47477
NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause a stack-based buffer overflow. A successful exploit of this vulnerability might lead to denial of service...
CVE-2026-47477
NVIDIA Triton Inference Server for Linux contains a vulnerability where an attacker can cause a stack-based buffer overflow. A successful exploit of this vulnerability might lead to denial of service...
CVE-2026-47476
CVE-2026-47476 affects the NVIDIA Triton Inference Server for Linux. The vulnerability allows an attacker to trigger uncontrolled resource consumption, with potential denial of service. The public documents consistently describe this as a DoS risk, but do not provide exploit details or precise ro...
Security Bulletin: NVIDIA Triton Inference Server - July 2026
NVIDIA has released a software update for NVIDIA® Triton Inference Server. To protect your system, clone or update this software to Triton Server r26.05 or later from the NVIDIA Triton Inference Server GitHub repo. Go to NVIDIA Product Security. Details The following table summarizes the potentia...
PT-2026-58759
Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server for Linux affected versions not specified Description A stack-based buffer overflow exists in the software, which occurs when a program writes more data to a buffer located on the stack than the buffer is allocat...
PT-2026-58761
Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server for Linux affected versions not specified Description An issue exists that allows an attacker to cause uncontrolled resource consumption. This flaw is network exploitable and requires no authentication, which may...
PT-2026-58762
Name of the Vulnerable Software and Affected Versions NVIDIA Triton Inference Server for Linux affected versions not specified Description An issue exists where an attacker can trigger an uncaught exception. This flaw is network exploitable and requires no authentication, which may lead to a deni...
PYSEC-2026-3064 SGLang: Reachable Assertion via lora_path in LoRAManager enables remote Denial of Dervice
A security vulnerability has been detected in SGLang 0.5.10.post1. Impacted is an unknown function of the file python/sglang/srt/lora/loramanager.py of the component Inference HTTP Endpoint. Such manipulation of the argument lorapath leads to reachable assertion. The attack can be launched...
PYSEC-2026-3060 Amazon SageMaker Python SDK is missing integrity verification in its Triton inference handler
Summary Amazon SageMaker Python SDK is an open-source library for training and deploying machine learning models on Amazon SageMaker. An issue exists where, under certain circumstances, the Triton inference handler deserializes model artifacts without performing integrity verification, allowing...
PYSEC-2026-3211 Type confusion leading to segfault in Tensorflow
Impact The implementation of shape inference for ConcatV2 can be used to trigger a denial of service attack via a segfault caused by a type confusion: python import tensorflow as tf @tf.function def test: y = tf.rawops.ConcatV2 values=1,2,3,4,5,6, axis = 0xb500005b return y test The axis argument...
PYSEC-2026-3249 Out of bounds read in Tensorflow
Impact TensorFlow's type inference can cause a heap OOB read as the bounds checking is done in a DCHECK which is a no-op during production: cc if nodet.typeid != TFTUNSET int ix = inputidxi; DCHECKix nodet.argssize "input " i " should have an output " ix " but instead only has " nodet.argssize "...
PYSEC-2026-3241 Crash when type cannot be specialized in Tensorflow
Impact Under certain scenarios, TensorFlow can fail to specialize a type during shape inference: cc void InferenceContext::PreInputInit const OpDef& opdef, const std::vector& inputtensors, const std::vector& inputtensorsasshapes const auto ret = fulltype::SpecializeTypeattrs, opdef;...
PYSEC-2026-3121 Out of bounds read in Tensorflow
Impact The implementation of shape inference for ReverseSequence does not fully validate the value of batchdim and can result in a heap OOB read: python import tensorflow as tf @tf.function def test: y = tf.rawops.ReverseSequence input = 'aaa','bbb', seqlengths = 1,1,1, seqdim = -10, batchdim = -...
PYSEC-2026-3113 Abort caused by allocating a vector that is too large in Tensorflow
Impact During shape inference, TensorFlow can allocate a large vector based on a value from a tensor controlled by the user: cc const auto numdims = Valueshapedim; std::vector dims; dims.reservenumdims; Patches We have patched the issue in GitHub commit 1361fb7e29449629e1df94d44e0427ebec8c83c7. T...
PYSEC-2026-3159 Integer overflow in Tensorflow
Impact The implementation of shape inference for Dequantize is vulnerable to an integer overflow weakness: python import tensorflow as tf input = tf.constant1,1,dtype=tf.qint32 @tf.function def test: y = tf.rawops.Dequantize input=input, minrange=1.0, maxrange=10.0, mode='MINCOMBINED',...
CVE-2026-54698 Hasura: Row-level authorization bypass on table computed fields
Hasura is an open-source product that provides users GraphQL or REST APIs. Prior to 2.49.2 and 2.45.5, a user can use a where clause on a table computed field returning SETOF sometable to infer row values that ought to be filtered for their role based on sometable's row-level permissions. While...
PYSEC-2026-2023 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...
PYSEC-2026-1966 code injection vulnerability exists in the huggingface/text-generation-inference repository
A code injection vulnerability exists in the huggingface/text-generation-inference repository, specifically within the autodocs.yml workflow file. The vulnerability arises from the insecure handling of the github.headref user input, which is used to dynamically construct a command for installing ...
Regular Expression Denial of Service (ReDoS)
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Regular Expression Denial of Service ReDoS via the structuredoutputs.regex parameter, which allows user-supplied regular expressions to be passed...
