CVE-2026-90878

vLLM (vllm-project) versions up to 0.27.1 are affected by a resource consumption vulnerability in the Jinja Template Rendering component of the /v1/chat/completions endpoint. The root cause is manipulation of the chat_template argument, allowing a remote attacker with low privileges to trigger ex...

GHSA-FMQH-XP37-5HR8 Open WebUI: Channel members can overwrite another member's message via the chat completions endpoint

Summary Any member of a channel who can post to it could also replace the text of a message written by a different member. The channel branch of the chat completions endpoint checked that the caller may write to the channel, and that the targeted message belongs to that channel, but never checked...

GHSA-3PF7-Q2G3-WJ28 Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions

Summary The chat-completions endpoint reads a folder id out of the request body and saves the newly created chat into that folder without checking that the caller is allowed to write there. Any authenticated user who knows a folder's id can put a chat of their own into another user's folder,...

CVE-2026-87997 Open WebUI: Any authenticated user can inject chats into another user's folder via chat completions

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.10.0 until 0.11.1, POST /api/chat/completions and POST /api/v1/chat/completions in backend/openwebui/main.py copied a client-supplied folderid into a new chat without applying the folder write-access chec...

SUSE CVE-2026-73556

vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structuredoutputs.regex parameter in vllm/v1/structuredoutput/backendlmformatenforcer.py is passed to lmformatenforcer.RegexParser without compileregexwithtimeout or validation in...

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...

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 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-2026-15974 CVE-2026-15974

SGLang contains an SSRF and local file read in the multimodal generation endpoint /v1/chat/completions due to unsanitized imageurl, allowing access to internal metadata, secrets, and services...

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...

EUVD-2026-41925

vLLM denial of service via prompt embeds on M-RoPE models...

Open WebUI: Authenticated users can bypass model access control via exposed query parameter [AI-ASSISTED]

SummaryAn internal-only bypassfilter parameter is exposed on the /openai/chat/completions and /ollama/api/chat HTTP endpoints via FastAPI query string binding, allowing any authenticated user to append ?bypassfilter=true and bypass model access control checks to invoke admin-restricted models...

CVE-2026-55514

A flaw was found in vLLM, a library for Large Language Model LLM inference and serving. A remote attacker, authorized to make a /v1/completions request, can send a specially crafted prompt embeds payload. This action causes the EngineCore to fail an assertion and fatally crash, leading to a Denia...

vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially crafted `chat_template_kwargs`

SummaryThe /v1/chat/completions and /tokenize endpoints allow a chattemplatekwargs request parameter that is used in the code before it is properly validated against the chat template. With the right chattemplatekwargs parameters, it is possible to block processing of the API server for long...

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...

CVE-2026-55514

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...

PYSEC-2026-2303

vLLM is a library for LLM inference and serving. From 0.12.0 to before 0.24.0, sending a pure prompt embeds payload in a /v1/completions request with a model using M-RoPE causes EngineCore to fail an assertion and fatally crash, shutting down the entire server application. Any remote user who is...