PT-2026-59758

Impact Certain TFLite models that were created using TFLite model converter would crash when loaded in the TFLite interpreter. The culprit is that during quantization the scale of values could be greater than 1 but code was always assuming sub-unit scaling. Thus, since code was calling...

PT-2026-59805

Impact An attacker can craft a TFLite model that would trigger a division by zero in BiasAndClamp implementation: cc inline void BiasAndClampfloat clamp min, float clamp max, int bias size, const float bias data, int array size, float array data // ... TFLITE DCHECK EQarray size % bias size, 0; /...

Linux Distros Unpatched Vulnerability : CVE-2026-43825

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Untrusted Java Deserialization in Apache OpenNLP SvmDoccatModel Versions Affected: before 3.0.0-M4 libsvm document categorization module; introduced in...

DEBIAN-CVE-2026-15123

Inappropriate implementation in DOM in Google Chrome prior to 150.0.7871.115 allowed a remote attacker to potentially exploit heap corruption via a crafted HTML page. Chromium security severity: High...

CVE-2026-54499 Stanza: Remote Code Execution via Unsafe Pickle Deserialization in Model Loaders

Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders such as stanza.models.common.pretrain.Pretrain.load attempt torch.load..., weightsonly=True but fall back to torch.load...,...

CVE-2026-54499

Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders such as stanza.models.common.pretrain.Pretrain.load attempt torch.load..., weightsonly=True but fall back to torch.load...,...

CVE-2026-54499 Stanza: Remote Code Execution via Unsafe Pickle Deserialization in Model Loaders

Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders such as stanza.models.common.pretrain.Pretrain.load attempt torch.load..., weightsonly=True but fall back to torch.load...,...

EUVD-2026-42474

Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders such as stanza.models.common.pretrain.Pretrain.load attempt torch.load..., weightsonly=True but fall back to torch.load...,...

CVE-2026-54499

CVE-2026-54499 affects Stanza prior to 1.12.2, where model loading uses torch.load(..., weights_only=True) and on an attacker-controllable pickle.UnpicklingError falls back to weights_only=False, enabling arbitrary pickle code execution when loading a malicious .pt pretrain/file. The vulnerabilit...

CVE-2026-54499 Stanza: Remote Code Execution via Unsafe Pickle Deserialization in Model Loaders

Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders such as stanza.models.common.pretrain.Pretrain.load attempt torch.load..., weightsonly=True but fall back to torch.load...,...

CVE-2026-59820

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.7-stable, LiteLLM Skills archive extraction did not sufficiently validate file paths from uploaded skill ZIP archives, allowing an authenticated user with access to LiteLLM LLM API routes or a key whos...

CVE-2026-44512

Open Neural Network Exchange ONNX is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.versionconverter.convertversion can dereference a null pointer in Upsample67::adaptupsample67 in onnx/versionconverter/adapters/upsample67.h when processing an untrusted mod...

EUVD-2026-42355

Open Neural Network Exchange ONNX is an open standard for machine learning interoperability. From 1.9.0 before 1.22.0, onnx.versionconverter.convertversion can dereference a null pointer in Upsample67::adaptupsample67 in onnx/versionconverter/adapters/upsample67.h when processing an untrusted mod...

MINI-G63V-2842-42CF

Bulletin has no description...

MINI-X74J-2J4M-892P

Bulletin has no description...

DRUPAL-CONTRIB-2026-076

The AI SEO/GEO Analyzer module generates SEO/GEO analysis reports by sending content of an entity including its comments to an LLM, then converts the model's Markdown response to HTML and stores it for display to privileged users. The generated HTML was rendered without passing through Drupal's...

Arbitrary Command Injection

Overview openllm is an OpenLLM: Self-hosting LLMs Made Easy. Affected versions of this package are vulnerable to Arbitrary Command Injection via the asyncruncommand function in the Model Repository Directory Name Handler process. An attacker can execute arbitrary system commands by manipulating t...

EUVD-2026-42290

An OS command injection vulnerability exists in the savesyslogtofile function of the "httpd" binary in Cisco RV130/RV130W with firmware 1.0.3.55 and RV110W routers with firmware 1.2.2.5 / 1.2.2.8. The modelname configuration parameter is not properly sanitized, which could allow an authenticated...

PYSEC-2026-2089

A vulnerability was found in bentoml OpenLLM 0.6.30. This affects the function asyncruncommand of the file src/openllm/common.py of the component Model Repository Directory Name Handler. Performing a manipulation of the argument cmd results in command injection. Attacking locally is a requirement...

CVE-2026-15035

Bentoml OpenLLM 0.6.30 is affected by a command-injection in async_run_command (src/openllm/common.py, Model Repository Directory Name Handler). The vulnerability stems from manipulation of the cmd argument, enabling local exploitation. Public exploit details exist, and attack requires local acce...