CVE-2026-100654

vLLM before 0.29.0 accepts user-controlled stoptokenids on the OpenAI-compatible POST /v1/completions and POST /v1/chat/completions endpoints but validates only that the values are integers, not that each token id is within the model vocabulary/logits range. When mintokens 0, the stop token ids a...

PT-2026-99325

Name of the Vulnerable Software and Affected Versions vLLM versions prior to 0.29.0 Description The software fails to validate if the values provided in stop token ids are within the model vocabulary or logits range, checking only that they are integers. When min tokens is greater than 0, these I...

PT-2026-80675

Summary The /v1/completions request model accepts prompt as a list of text prompts or a list of token-id prompts without any outer prompt-count bound. The serving path turns each element into a separate engine input, creates one engine generator per element, merges all generators, and allocates a...

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-2026-73556: Uncontrolled Resource Consumption

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...

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...

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-2026-55514: Reachable Assertion

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...

CVE-2025-48942

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

CVE-2025-48942: Uncaught Exception

vLLM is an inference and serving engine for large language models LLMs. In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid jsonschema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex...

GHSA-6QC9-V4R8-22XG vLLM DOS: Remotely kill vllm over http with invalid JSON schema

Summary Hitting the /v1/completions API with a invalid jsonschema as a Guided Param will kill the vllm server Details The following API call venv derekh@ip-172-31-15-108 $ curl -s http://localhost:8000/v1/completions -H "Content-Type: application/json" -d '"model":...

PT-2025-12092

Name of the Vulnerable Software and Affected Versions vllm versions 0.5.2.2 Description The issue is related to Denial of Service attacks. It occurs in the "POST /v1/completions" and "POST /v1/embeddings" endpoints. For "POST /v1/completions", enabling use beam search and setting best of to a hig...