PT-2026-59395

Ollama Model Access Control Bypass via /api/generate, /api/embed, /api/embeddings, and /api/show Affected Component Ollama proxy endpoints missing model access control: - backend/open webui/routers/ollama.py lines 955-995, generate completion - backend/open webui/routers/ollama.py lines 835-881,...

PT-2026-59402

Summary Open WebUI lets a user who can create, update, or import workspace models store arbitrary meta.knowledge entries on their model without checking whether they own or can read the referenced files. Open WebUI then treats meta.knowledge entries of type file as an authorization source in two...

PT-2026-59679

Summary Amazon SageMaker Python SDK is an open-source library for training and deploying machine learning models on Amazon SageMaker. An issue exists where, under certain circumstances, the ModelBuilder/Serve component stores an HMAC signing key in cleartext as a container environment variable,...

PT-2026-59508

Local file inclusion LFI and server-side request forgery SSRF vulnerabilities in pgAdmin 4 LLM API configuration endpoints. User-supplied api key file and api url preferences were passed to the LLM provider clients without validation. An authenticated user could read arbitrary server-side files b...

PT-2026-59362

Base Model Routing Bypasses Access Control via Model Chaining Affected Component Model chaining via base model id: - backend/open webui/routers/models.py lines 170-214, create new model - backend/open webui/routers/models.py lines 254-308, import models - backend/open webui/main.py lines 1696-171...

PT-2026-59799

Impact A malicious invalid input crashes a tensorflow model Check Failed and can be used to trigger a denial of service attack. To minimize the bug, we built a simple single-layer TensorFlow model containing a Convolution3DTranspose layer, which works well with expected inputs and can be deployed...

PT-2026-59490

OpenMed before 1.5.2 contains a remote code execution vulnerability in the PII privacy-filter model loading path. The privacy-filter dispatcher used broad substring matching on the user-supplied model name parameter, allowing a value such as attacker/foo-privacy-filter-bar to route through a path...

PT-2026-59309

In mlflow/mlflow versions up to 3.9.0, the SearchModelVersions REST API endpoint and the mlflowSearchModelVersions GraphQL query lack proper per-model authorization checks when basic authentication is enabled. This allows any authenticated user to enumerate all model versions across all registere...

PT-2026-59745

Impact When converting transposed convolutions using per-channel weight quantization the converter segfaults and crashes the Python process. python import tensorflow as tf class QuantConv2DTransposedtf.keras.layers.Layer: def buildself, input shape: self.kernel = self.add weight"kernel", 3, 3,...

PT-2026-59254

LiteLLM prior to 1.83.10 allows a user to modify their own user role via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user who can reach this endpoint can set their role to proxy...

PT-2026-59308

MLflow 3.9.0 with basic-auth --app-name basic-auth fails to enforce authorization checks for multiple Gateway API 'list' endpoints. Specifically, the BEFORE REQUEST HANDLERS dictionary in mlflow/server/auth/ init .py does not include entries for ListGatewaySecretInfos, ListGatewayEndpoints, and...

PT-2026-57888

Name of the Vulnerable Software and Affected Versions OpenClaw versions prior to 2026.6.8 Description An authorization bypass exists in OpenAI-compatible HTTP model overrides. This issue allows callers with lower trust levels to perform actions that typically require stronger authorization checks...

PT-2026-59361

Summary Several direct, index-addressed Ollama proxy routes accept a caller-supplied url idx path parameter and use it as a raw index into the admin-configured OLLAMA BASE URLS list. Access control on these routes validates only whether the user may use the requested model, never which backend th...

PT-2026-59182

A flaw was found in InstructLab. The linux train.py script hardcodes trust remote code=True when loading models from HuggingFace. This allows a remote attacker to achieve arbitrary Python code execution by convincing a user to run ilab train/download/generate with a specially crafted malicious...

PT-2026-59380

Summary An application-wide Cross-Site Request Forgery CSRF vulnerability was found Open-WebUl's image uploading functionality. An attacker can set an image URL to a malicious endpoint, allowing them to perform actions on behalf of a victim user. Any authenticated user can exploit this...

PT-2026-59376

Summary The /responses endpoint in the OpenAI router accepts any authenticated user and forwards requests directly to upstream LLM providers without enforcing per-model access control. While the primary chat completion endpoint generate chat completion checks model ownership, group membership, an...

PT-2026-59369

Summary A user can modify another user's model even if its visibility is set to Private. The finding resulted from a penetration test for a customer. It is suspected that the root cause of the issue lies within the core of Open WebUI, which is why it is being reported as a security issue here...

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...

PT-2026-59687

The snorkel library thru v0.10.0 contains an insecure deserialization vulnerability CWE-502 in the Trainer.load method of the Trainer class. The method loads model checkpoint files using torch.load without enabling the security-restrictive weights only=True parameter. This default behavior allows...

PT-2026-59335

Summary Null pointer dereference SIGSEGV in Upsample 6 7::adapt upsample 6 7 onnx/version converter/adapters/upsample 6 7.h:31 when convert version processes a model with an Upsample node that has zero inputs. The adapter accesses node-inputs0-sizes without checking input count. 107-byte PoC...