Astra Linux – Vulnerability in Linux 5.10

In the Linux kernel, the following vulnerability has been resolved: bus: mhi: core: Validate channel ID when processing command completions MHI reads the channel ID from the event ring element sent by the device, which can be any value between 0 and 255. To prevent out-of-bounds accesses, a check...

Xinference vulnerable to remote code execution via unsafe `eval()` in Llama3 tool-call parsing

Summary Xinference used Python's unsafe eval function when parsing Llama3 tool-call output generated by a large language model. Because the model output can be influenced by attacker-controlled prompts sent to the chat completion API, a remote attacker can craft prompts that cause the model to...

EUVD-2026-64146

Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval in xinference/model/llm/toolparsers/llama3toolparser.py and xinference/model/llm/utils.py. Requests to...

CVE-2026-72046

In the Linux kernel, the following vulnerability has been resolved: gve: fix header buffer corruption with header-split and HW-GRO The DQO RX datapath programs a per-buffer-queue-descriptor headerbufaddr at post time and reads the split header back at completion time. Both the post and the read...

CVE-2026-72046

The CVE-2026-72046 issue in the Linux kernel concerns the gve RX path, where header buffers were indexed by buffer-queue position (bufq->tail) for posts and by the completion index (desc_idx) for reads. With HW-GRO and multi-flow traffic, out-of-order completions cause headers to be read from ...

CVE-2026-73559

A flaw was found in vLLM, an inference and serving engine for large language models. An authenticated API client can exploit this vulnerability by sending a single request to the /v1/completions endpoint with an excessively large list of prompts. This unbounded input causes the vLLM server to...

CVE-2026-73559

vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.26.0, the /v1/completions CompletionRequest.prompt field in vllm/entrypoints/openai/completion/protocol.py accepts an unbounded liststr or listlistint, prompttoseq in vllm/renderers/inputs/preprocess.py and...

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...

PT-2026-71672

Name of the Vulnerable Software and Affected Versions vLLM versions 0.20.2rc0 through 0.25.x Description A race condition exists in the safe load prompt embeds function within vllm/renderers/embed utils.py when enable prompt embeds is enabled. The issue occurs because torch.sparse.check sparse...

EUVD-2026-54283

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

DEBIAN-CVE-2026-43628

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-43628

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

UBUNTU-CVE-2026-43628

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-43628 llama.cpp b3978–b9058 Integer Underflow via DRY Sampler

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-43628 llama.cpp b3978–b9058 Integer Underflow via DRY Sampler

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dryallowedlength set to INT32MIN to the /v1/completions or...

CVE-2026-70484

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Summary An authenticated user whose features.imagegeneration permission has been revoked can still make the server generate images by sending the feature flag in a chat-completion request. The chat pipeline took the client-supplied features object at face value and never re-checked the permission...

CVE-2026-70484 Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

CVE-2026-70484 Open WebUI: Users denied the image-generation permission can still generate images via chat completions

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 until 0.11.0, the legacy chat-completions features block trusted a client-supplied imagegeneration flag and did not re-check the features.imagegeneration permission that the direct image routes and...

CVE-2026-70484

Open WebUI vulnerability CVE-2026-70484 affects the self-hosted AI platform Open WebUI in versions 0.7.0 through 0.11.0. The legacy chat-completions features did not re-check the features.image_generation permission enforced on direct image routes and native function-calling paths, allowing an au...