PT-2026-59828

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.raw ops.ConcatV2 values=1,2,3,4,5,6, axis = 0xb500005b return y test The axis argumen...

PT-2026-59739

Impact The implementation of shape inference for ReverseSequence does not fully validate the value of batch dim and can result in a heap OOB read: python import tensorflow as tf @tf.function def test: y = tf.raw ops.ReverseSequence input = 'aaa','bbb', seq lengths = 1,1,1, seq dim = -10, batch di...

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...

Hugging Face Text Generation Inference vulnerable to Uncontrolled Resource Consumption

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2025-12060 via keras (2.12.0rc0)

keras PYPI version 2.12.0rc0 is affected by a known vulnerability. The following packages have a transitive dependency on keras and may be impacted: - mlopspython-inference =67580760626172675.0.0, =757069802391466481559610331145 Source cves: CVE-2025-12060 Source advisory: OSV:PYSEC-2026-1486...

mlopspython-inference (>=67580760626172675.0.0, <=757069802391466481559610331145) potentially affected by CVE-2025-12058 via keras (2.12.0rc0)

keras PYPI version 2.12.0rc0 is affected by a known vulnerability. The following packages have a transitive dependency on keras and may be impacted: - mlopspython-inference =67580760626172675.0.0, =757069802391466481559610331145 Source cves: CVE-2025-12058 Source advisory: OSV:PYSEC-2026-1487...

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...

vLLM Tool Schema allows DoS via Malformed pattern and type Fields

SummaryThe 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 ...

onnx onnxruntime old.cc convPoolShapeInference_opset19 out-of-bounds

...

From Regression to Prior-Aware Inference: Solving the ILWE Family in Randomness Leakage Attacks against ML-DSA

ML-DSA is a representative lattice-based signature scheme standardized by NIST. It relies on signing randomness and rejection sampling to ensure that released signatures are statistically independent of the secret key. Practical implementations, however, may leak partial information about this...

lazyllm-verl (0.3.2.dev1), londonaicentre-mesa-local (>=2.8.0, <=2.8.1) +1 more potentially affected by CVE-2026-55646 via vllm (>=0.22.0, <=0.23.0)

vllm PYPI version =0.22.0, =2.8.0, =2.1.3, =2.2.4 Source cves: CVE-2026-55646 Source advisory: SNYK:PYTHON-VLLM-17872258...

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...

lazyllm-verl (0.3.2.dev1), londonaicentre-mesa-local (>=2.8.0, <=2.8.1) +1 more potentially affected by CVE-2026-55646 via vllm (>=0.22.0, <=0.23.0)

vllm PYPI version =0.22.0, =2.8.0, =2.1.3, =2.2.4 Source cves: CVE-2026-55646 Source advisory: OSV:PYSEC-2026-2305...

lazyllm-verl (0.3.2.dev1), londonaicentre-mesa-local (>=2.8.0, <=2.8.1) +1 more potentially affected by CVE-2026-55646 via vllm (>=0.22.0, <=0.23.0)

vllm PYPI version =0.22.0, =2.8.0, =2.1.3, =2.2.4 Source cves: CVE-2026-55646 Source advisory: MEND:CVE-2026-55646...

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (ROCm)

Red Hat AI Inference Server 3.2.2 ROCm is now available. Red Hat® AI Inference Server...

Important: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)

Red Hat AI Inference Server 3.2.2 CUDA is now available. Red Hat® AI Inference Server...

Important: Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.2.2 (cuda)

Red Hat AI Inference Server Model Optimization Tools 3.2.2 cuda is now available. Red Hat® AI Inference Server Model Optimization Tools...

Out-of-bounds Read

Overview onnx is an Open Neural Network Exchange Affected versions of this package are vulnerable to Out-of-bounds Read through convPoolShapeInferenceopset19 in onnx/defs/nn/old.cc. An attacker can trigger the flaw by supplying a malformed convolution or pooling model that reaches the...

CVE-2026-14647 onnx onnxruntime old.cc convPoolShapeInference_opset19 out-of-bounds

A weakness has been identified in onnx up to 1.21.x. This vulnerability affects the function convPoolShapeInferenceopset19 of the file onnx/defs/nn/old.cc of the component onnxruntime. This manipulation causes out-of-bounds read. It is possible to initiate the attack remotely. The exploit has bee...