vger

V'ger V'ger is an interactive command-line application for post-exploitation of authenticated Jupyter instances with a focus on AI/ML security operations. User Stories As a Red Teamer , you've found Jupyter credentials, but don't know what you can do with them. V'ger is organized in a format that...

A Malicious Webpage Could Poison Your Local AI Model Behind NVIDIA NemoClaw

Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself. The findings were shared with The Hacker News ahead of...

PT-2026-81516

Name of the Vulnerable Software and Affected Versions NVIDIA NemoClaw versions 0.0.0 through 0.0.25 Description NVIDIA NemoClaw for Linux contains a flaw in its inference server setup that allows a remote attacker to access the inference service without authentication. In affected configurations,...

EUVD-2026-62958

In Splunk AI Toolkit versions below 6.0.0, a user who can upload models could overwrite a model being uploaded by another user by sending a concurrent upload request for the same model name, causing the resulting model lookup entry to reference attacker-controlled content. The race condition is...

CVE-2026-12261

A vulnerability in nltk.downloader in nltk/nltk versions = 3.9.4 allows for cross-package resource and model poisoning. The downloader extracts package archives into shared namespaces such as corpora/ and taggers/ instead of package-isolated roots, and validates package integrity only after the...

PT-2026-59163

Predictable bucket naming in Vertex AI Experiments in Google Cloud Vertex AI from version 1.21.0 up to but not including 1.133.0 on Google Cloud Platform allows an unauthenticated remote attacker to achieve cross-tenant remote code execution, model theft, and poisoning via pre-creating predictabl...

PYSEC-2026-1645 Undefined Behavior in mlflow

A vulnerability in mlflow/mlflow version 2.11.1 allows attackers to create multiple models with the same name by exploiting URL encoding. This flaw can lead to Denial of Service DoS as an authenticated user might not be able to use the intended model, as it will open a different model each time...

EUVD-2025-210423

Picklescan before 0.0.33 fails to detect the numpy.f2py.crackfortran.getlincoef gadget in pickle reduce methods, allowing arbitrary code execution. Attackers can craft malicious pickle files that execute arbitrary Python code when loaded, bypassing Picklescan's safety checks and enabling...

CVE-2026-2651 Missing Authorization Validation in mlflow/mlflow

A vulnerability in MLflow versions =3.10.1.dev0 allows unauthorized access to multipart upload MPU endpoints when the --serve-artifacts mode is enabled. The authorization logic does not enforce resource-level permission checks for /mlflow-artifacts/mpu/ endpoints, enabling attackers to overwrite...

CVE-2026-2651 Missing Authorization Validation in mlflow/mlflow

A vulnerability in MLflow versions =3.10.1.dev0 allows unauthorized access to multipart upload MPU endpoints when the --serve-artifacts mode is enabled. The authorization logic does not enforce resource-level permission checks for /mlflow-artifacts/mpu/ endpoints, enabling attackers to overwrite...

CVE-2026-2651

MLflow CVE-2026-2651 describes missing authorization validation for MPU endpoints under /mlflow-artifacts/mpu/* when serve-artifacts is enabled. Vulnerable in MLflow versions

Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models

Unified autoregressive models UAMs are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared parameters and a multimodal vocabulary simplify the training pipeline and facilitate flexible multimodal generation, yet might introduce new...

PYSEC-2026-99

NLTK versions =3.9.2 are vulnerable to arbitrary code execution due to improper input validation in the StanfordSegmenter module. The module dynamically loads external Java .jar files without verification or sandboxing. An attacker can supply or replace the JAR file, enabling the execution of...

PYSEC-2026-99

NLTK versions =3.9.2 are vulnerable to arbitrary code execution due to improper input validation in the StanfordSegmenter module. The module dynamically loads external Java .jar files without verification or sandboxing. An attacker can supply or replace the JAR file, enabling the execution of...

CVE-2026-0848 Arbitrary Code Execution in NLTK StanfordSegmenter via Untrusted JAR Loading

NLTK versions =3.9.2 are vulnerable to arbitrary code execution due to improper input validation in the StanfordSegmenter module. The module dynamically loads external Java .jar files without verification or sandboxing. An attacker can supply or replace the JAR file, enabling the execution of...

NLTK 输入验证错误漏洞

NLTK is an open-source natural language toolkit developed by NLTK. It is used to support research and development in natural language processing. Versions of NLTK 3.9.2 and earlier contained a vulnerability related to input validation errors. This vulnerability stemmed from improper input...

GHSA-WH2J-26J7-9728 Google Cloud Vertex AI has a a vulnerability involving predictable bucket naming

Predictable bucket naming in Vertex AI Experiments in Google Cloud Vertex AI from version 1.21.0 up to but not including 1.133.0 on Google Cloud Platform allows an unauthenticated remote attacker to achieve cross-tenant remote code execution, model theft, and poisoning via pre-creating predictabl...

Missing Authorization Validation on MLflow MPU Endpoints Leads to Cross-Resource Artifact Overwrite, Model Poisoning, and Cross-Boundary Command Execution on Model Load

Analyzed version: 5af88dc08a54d40dddfc019da9e7f0fd0fcf34e2 git describe: nightly-2300-g5af88dc08, local mlflow.version: 3.10.1.dev0 In --serve-artifacts mode, MLflow exposes MPU endpoints for large-file multipart uploads. However, its authorization logic only covers the /mlflow-artifacts/artifact...

Microsoft Develops Scanner to Detect Backdoors in Open-Weight Large Language Models

Microsoft on Wednesday said it built a lightweight scanner that it said can detect backdoors in open-weight large language models LLMs and improve the overall trust in artificial intelligence AI systems. The tech giant's AI Security team said the scanner leverages three observable signals that ca...

GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs

Text-attributed graphs TAGs, which combine structural and textual node information, are ubiquitous across many domains. Recent work integrates Large Language Models LLMs with Graph Neural Networks GNNs to jointly model semantics and structure, resulting in more general and expressive models that...