109 matches found
CVE-2026-73557
vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...
CVE-2026-73557
vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...
CVE-2026-73557 vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts
vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safeloadpromptembeds in vllm/renderers/embedutils.py uses torch.sparse.checksparsetensorinvariants, whose process-global save, enable, and restore state can be raced by concurrent promptembeds parts...
CVE-2026-70488
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.9.6 until 0.11.0, the sync cleanup endpoint authorized write access to the knowledge base in the URL but then acted on directory and file ids supplied in the request body without checking that those objec...
Open WebUI: Deletion of directories and file embeddings in other knowledge bases via sync cleanup
Summary A user with write access to one knowledge base could delete directories, and drop file embeddings, belonging to knowledge bases they do not control. The sync cleanup endpoint verified write access on the knowledge base named in the URL and then acted on the directory and file ids supplied...
GHSA-JXC9-XMC4-GR23 Open WebUI: Deletion of directories and file embeddings in other knowledge bases via sync cleanup
Summary A user with write access to one knowledge base could delete directories, and drop file embeddings, belonging to knowledge bases they do not control. The sync cleanup endpoint verified write access on the knowledge base named in the URL and then acted on the directory and file ids supplied...
CVE-2026-70488 Open WebUI: Deletion of directories and file embeddings in other knowledge bases via sync cleanup
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.9.6 until 0.11.0, the sync cleanup endpoint authorized write access to the knowledge base in the URL but then acted on directory and file ids supplied in the request body without checking that those objec...
CVE-2026-70488
CVE-2026-70488 – Open WebUI : In Open WebUI builds from 0.9.6 to 0.11.0, the sync cleanup endpoint (POST /api/v1/knowledge/{id}/sync/cleanup) did not properly constrain actions to the target knowledge base. The handler authenticated write access via the URL knowledge base, then acted on directory...
CVE-2026-70488 Open WebUI: Deletion of directories and file embeddings in other knowledge bases via sync cleanup
Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.9.6 until 0.11.0, the sync cleanup endpoint authorized write access to the knowledge base in the URL but then acted on directory and file ids supplied in the request body without checking that those objec...
CVE-2026-14133
A race flaw was found in the History Embeddings component of the Chromium browser. Upstream bugs: https://code.google.com/p/chromium/issues/detail?id=514039947...
GHSA-33CG-GXV8-3P8G vLLM denial of service via prompt embeds on M-RoPE models
Summary Short summary of the problem. Make the impact and severity as clear as possible. For example: An unsafe deserialization vulnerability allows any unauthenticated user to execute arbitrary code on the server. Sending a pure prompt embeds payload in a /v1/completions request with a model usi...
PYSEC-2026-2019 vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
Summary Users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape e.g. hidden dimension is wrong, regardless of whether the model is intended to support such inputs as defined in the Supported Models page. The issue has...
SUSE CVE-2026-14133
Race in History Embeddings in Google Chrome prior to 150.0.7871.47 allowed a remote attacker to perform UI spoofing via a crafted HTML page. Chromium security severity: Low...
Reachable Assertion
Overview vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs Affected versions of this package are vulnerable to Reachable Assertion via the /v1/completions endpoint when processing pure prompt embeds with M-RoPE models. An attacker can cause the server to cras...
Chromium: CVE-2026-14133 Race in History Embeddings
This CVE was assigned by Chrome. Microsoft Edge Chromium-based ingests Chromium, which addresses this vulnerability. Please see Google Chrome Releases for more information...
EUVD-2026-40820
Race in History Embeddings in Google Chrome prior to 150.0.7871.47 allowed a remote attacker to perform UI spoofing via a crafted HTML page. Chromium security severity: Low...
CVE-2026-14133
Race in History Embeddings in Google Chrome prior to 150.0.7871.47 allowed a remote attacker to perform UI spoofing via a crafted HTML page. Chromium security severity: Low...
DEBIAN-CVE-2026-14133
Race in History Embeddings in Google Chrome prior to 150.0.7871.47 allowed a remote attacker to perform UI spoofing via a crafted HTML page. Chromium security severity: Low...
