CVE 検索
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
公開されているすべての CVE とオープンソースのセキュリティアドバイザリ（NVD、OSV、GitHub）を、CVSS、EPSS、実際に悪用されているか（CISA KEV）とともに掲載しています。数時間ごとに更新されます。スキャンでは、検出した技術とこれらを照合します。
| 25/08/2026 |
| CVE-2026-73560 | 中6.5 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the MiMoV2OmniMultiModalProcessor in vllm/transformers_utils/processors/mimo_v2_omni.py passes attacker-controlled image and audio strings through _fetch_image, requests.get, and Image.open instead of MediaConnector, bypassing allowed_m | 17/08/2026 |
| CVE-2026-71486 | 中4.3 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts s | 17/08/2026 |
| CVE-2026-73559 | 中6.5 | 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 list[str] or list[list[int]], prompt_to_seq() in vllm/renderers/inputs/preprocess.py and OnlineRenderer.p | 13/08/2026 |
| CVE-2026-73558 | 中5.3 | vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of a | 13/08/2026 |
| CVE-2026-73557 | 中5.3 | vLLM is an inference and serving engine for large language models. From 0.20.2rc0 until 0.26.0, safe_load_prompt_embeds in vllm/renderers/embed_utils.py uses torch.sparse.check_sparse_tensor_invariants, whose process-global save, enable, and restore state can be raced by concurrent prompt_embeds parts submitted to POST | 13/08/2026 |
| CVE-2026-73556 | 中5.3 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the structured_outputs.regex parameter in vllm/v1/structured_output/backend_lm_format_enforcer.py is passed to lmformatenforcer.RegexParser without compile_regex_with_timeout or validation in validate_structured_output_request_lm_format | 13/08/2026 |
| CVE-2026-73555 | 中5.3 | vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, all | 13/08/2026 |
| CVE-2025-61620 | vLLM: Resource-Exhaustion (DoS) through Malicious Jinja Template in OpenAI-Compatible Server | 07/07/2026 |
| CVE-2025-9141 | vLLM has remote code execution vulnerability in the tool call parser for Qwen3-Coder | 07/07/2026 |
| CVE-2026-55574 | 高7.5 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, the structured_outputs.regex API parameter passes a user-supplied regular expression string directly to the grammar compiler backends with no compilation timeout; in the xgrammar backend the string reaches the regex c | 06/07/2026 |
| CVE-2026-55514 | 中6.5 | 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 authorized to make a /v | 06/07/2026 |
| CVE-2026-54234 | 高7.5 | vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Prior to 0.24.0, a frontend-legal multi-request speculative decoding workload can cause the rejection sampler to produce a recovered token equal to the model vocabulary size boundary value, which is then converted to negative one when | 06/07/2026 |
| CVE-2026-55646 | 中6.5 | vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload si | 06/07/2026 |
| CVE-2026-54236 | 中5.3 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to | 22/06/2026 |
| CVE-2026-54235 | 中6.5 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampli | 22/06/2026 |
| CVE-2026-54233 | 中6.5 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, vLLM's /v1/audio/transcriptions endpoint limits compressed upload size but not decoded PCM output. A 25MB OPUS file expands to ~14.9GB of float32 PCM at decode time. This vulnerability is fixed in 0.23.1rc0. | 22/06/2026 |
| CVE-2026-54232 | 高8.8 | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not | 22/06/2026 |