CVE-2026-42192

Plunk is an open-source email platform built on top of AWS SES. Prior to version 0.9.0, a stored cross-site scripting XSS vulnerability exists in the campaign management feature, where the email body content created by authenticated project members is stored and later rendered in the admin...

CVE-2026-31236

The CVE-2026-31236 issue affects the llm CLI tool up to version 0.27.1. The vulnerability arises from the --functions argument, which accepts user-provided Python definitions and is executed with unsafe exec() without sanitization or sandboxing, enabling arbitrary code execution on a victim’s sys...

cognee 安全漏洞

Cognee is an open-source tool developed by Topoteretes, designed to provide AI agents with shared memory and context management capabilities. Cognee versions prior to v0.4.0 contained security vulnerabilities. These vulnerabilities stemmed from the use of the unsafe exec function in notebook cell...

ludwig 安全漏洞

Ludwig is an open-source declarative deep learning framework developed by Ludwig. Versions of Ludwig 0.10.4 and earlier contain security vulnerabilities. These vulnerabilities stem from the predict method, which uses pandas.readpickle without proper validation when loading pickle files. This coul...

CVE-2026-31225

The superduper project thru v0.10.0 contains a critical remote code execution vulnerability in its query parsing component. The parseoppart function in query.py uses the unsafe eval function to dynamically evaluate user-supplied query operands without proper sanitization or restriction. Although...

CVE-2026-31230

The CVE-2026-31230 vulnerability concerns the Adversarial Robustness Toolbox (ART) up to v1.20.1, specifically in its Kubeflow component (robustness_evaluation_fgsm_pytorch.py). The issue arises from using unsafe eval() to parse string values passed via --clip_values and --input_shape, enabling a...

CVE-2026-31228

The connected documents confirm a vulnerability in the Adversarial Robustness Toolbox (ART) up to version 1.20.1, specifically in its Kubeflow component. The root cause is that the robustness evaluation function for PyTorch models uses Python’s unsafe eval() to dynamically evaluate user-supplied ...

Adversarial Robustness Toolbox 安全漏洞

Adversarial Robustness Toolbox is an open-source machine learning security defense and evaluation tool developed by Trusted-AI. Versions of Adversarial Robustness Toolbox 1.20.1 and earlier contained security vulnerabilities. These vulnerabilities stemmed from the robustness evaluation function i...

PT-2026-40117

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustness evaluation fgsm pytorch.py. The script uses the unsafe eval function to parse string values provided via the --clip values and --input shape command-lin...

LLM 安全漏洞

LLM is a multi-model large language model command-line interaction tool developed by Simon Willison. Versions of LLM 0.27.1 and earlier contain security vulnerabilities. These vulnerabilities stem from the use of the --functions command-line parameter to directly execute unsafe code using the exe...

CVE-2026-31225

The superduper project thru v0.10.0 contains a critical remote code execution vulnerability in its query parsing component. The parseoppart function in query.py uses the unsafe eval function to dynamically evaluate user-supplied query operands without proper sanitization or restriction. Although...

PT-2026-40118

Cognee thru v0.4.0 contains a critical remote code execution vulnerability in its notebook cell execution API endpoint. The endpoint is designed to execute arbitrary Python code provided by the user, but it does so using the unsafe exec function without any sandboxing, validation, or security...

superduper 安全漏洞

Superduper is an open-source database integration AI proxy and application building tool developed by superduper.io. Versions of Superduper prior to v0.10.0 contained security vulnerabilities. These vulnerabilities stemmed from the Parseoppart function in the query parsing component, which used t...

CVE-2026-31231

Cognee thru v0.4.0 contains a critical remote code execution vulnerability in its notebook cell execution API endpoint. The endpoint is designed to execute arbitrary Python code provided by the user, but it does so using the unsafe exec function without any sandboxing, validation, or security...

CVE-2026-31231

Cognee thru v0.4.0 contains a critical remote code execution vulnerability in its notebook cell execution API endpoint. The endpoint is designed to execute arbitrary Python code provided by the user, but it does so using the unsafe exec function without any sandboxing, validation, or security...

Machine Learning Engineering Open Book 安全漏洞

Machine Learning Engineering Open Book is a collection of methodologies for training and fine-tuning large language models developed by Stas Bekman. There is a security vulnerability in Machine Learning Engineering Open Book. This vulnerability arises from the use of the torch-checkpoint-shrink.p...

CVE-2026-31225

The vulnerability CVE-2026-31225 affects the superduper project up to v0.10.0. The issue is in the query parsing component: the function named in the code (_parse_op_part()/parse_op_part()) uses eval() on user-supplied operands with only a restricted global namespace, but does not block dangerous...

CVE-2026-31230

The Adversarial Robustness Toolbox ART thru 1.20.1 contains a command-line argument injection vulnerability in its Kubeflow component robustnessevaluationfgsmpytorch.py. The script uses the unsafe eval function to parse string values provided via the --clipvalues and --inputshape command-line...

Snorkel 安全漏洞

Snorkel is an open-source system developed by Snorkel that uses weak supervision to quickly generate training data. Versions of Snorkel prior to v0.10.0 contain security vulnerabilities. These vulnerabilities stem from the BaseLabeler class’s BaseLabeler.load method, which uses the unsafe...

TinyZero 安全漏洞

TinyZero is an inference model training tool developed by Jiayi Pan, based on reinforcement learning, and aimed at replicating the DeepSeek R1 Zero. TinyZero has a security vulnerability. This vulnerability stems from the copy function in the HDFS file manipulation tool, which insecurely construc...