CVE-2026-63378: fctr-id okta-ai-agent: TAKO AI Agent for Okta is a local-first AI agent that helps Okta administrators query tenant data using natural language

TAKO AI Agent for Okta is a local-first AI agent that helps Okta administrators query tenant data using natural language. Prior to 3.0.1-beta, any authenticated user with a valid fctrsession cookie can submit arbitrary Python source in the scriptcode field of POST /api/react/execute-script, witho...

EUVD-2026-110022

vLLM: Public multimodal SHM handle forgery reaches worker-side pickle.loads with insecure serialization disabled...

Seeq Server — Unauthenticated Self-Registration + Data Lab Jupyter Missing Autho — Detect

Fingerprint / reachability check for Seeq Server — Unauthenticated Self-Registration + Data Lab Jupyter Missing Authorization → Arbitrary Python RCE !/usr/bin/env python3 -- coding: utf-8 -- """Detection for Seeq Server — Unauthenticated Self-Registration + Data Lab Jupyter Missing Authorization ...

PT-2026-127745

Summary MLflow 3.12.0 introduced registration and deserialization support for third-party scorers in OSS MLflow. During scorer deserialization, the server accepts a request-controlled Python module path beneath one of four allowed package prefixes, imports that module, obtains a request-controlle...

PT-2026-127225

Name of the Vulnerable Software and Affected Versions MLflow versions 3.12.0 through 3.16.x Description Third-party scorer deserialization in mlflow/genai/scorers/base.py allows the import of request-selected descendants of allowed modules rather than requiring an exact match. An attacker can use...

PYSEC-2026-4345

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

PYSEC-2026-4345

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912

In versions prior to 0.32.0 , the vLLM inference and serving engine for large language models is vulnerable to arbitrary Python execution. An authenticated caller can exploit this by placing forged shared-memory address and monotonic_id values in public multimodal features.kwargs_data. In scale-o...

CVE-2026-115912

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

CVE-2026-115912 vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and monotonicid values in public multimodal features.kwargsdata. In scale-out deployments with shared-memory multimodal caching enabled, workers trust...

PT-2026-123435

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.32.0 Description An authenticated caller can provide forged shared-memory address and monotonic id values within the public multimodal features.kwargs data. In scale-out deployments where shared-memory multimodal cachi...

CVE-2026-57845

Hugging Face Datasets through 5.1.0 contains an insecure deserialization vulnerability that allows attackers to execute arbitrary Python code by crafting a malicious pickle file loaded through the deprecated pandas packaged builder. Attackers can supply a pickle-backed dataset that is processed b...

CVE-2026-57845

Hugging Face Datasets through 5.1.0 contains an insecure deserialization vulnerability that allows attackers to execute arbitrary Python code by crafting a malicious pickle file loaded through the deprecated pandas packaged builder. Attackers can supply a pickle-backed dataset that is processed b...

EUVD-2026-109092

Hugging Face Datasets through 5.1.0 contains an insecure deserialization vulnerability that allows attackers to execute arbitrary Python code by crafting a malicious pickle file loaded through the deprecated pandas packaged builder. Attackers can supply a pickle-backed dataset that is processed b...

PT-2026-122146

Hugging Face Datasets through 5.1.0 contains an insecure deserialization vulnerability that allows attackers to execute arbitrary Python code by crafting a malicious pickle file loaded through the deprecated pandas packaged builder. Attackers can supply a pickle-backed dataset that is processed b...

CVE-2026-114053

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

CVE-2026-114053

vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mmprocessorkwargs.coderevision to Transformers AutoProcessor.frompretrained, letting clients select which revision of a model's dynamic processor code is imported when trustremotecode is enabled. An attacker controlling a revision in the...

vLLM code injection vulnerability

Versions vLLM 0.7.3 through 0.31.0 contain a code injection vulnerability. This vulnerability arises when the mmprocessorkwargs.coderevision parameter provided by the request is passed to Transformers AutoProcessor.frompretrained. When trustremotecode is enabled, it allows clients to specify whic...