Vllm
Vulnerability activity for Vllm: what is being exploited, what was published lately, and when the next patch release is due.
Last 30 days
- CVEs
- 8
- Critical (CVSS 9+)
- 0
- Exploited (CISA KEV)
- 0
- With exploit code
- 0
Last 90 days
- CVEs
- 8
- Critical (CVSS 9+)
- 0
- Exploited (CISA KEV)
- 0
- With exploit code
- 0
Last 365 days
- CVEs
- 11
- Critical (CVSS 9+)
- 0
- Exploited (CISA KEV)
- 0
- With exploit code
- 0
Exploited now
None of this vendor's CVEs are on CISA's known-exploited list.
Recent
- 6.5MediumOct 26, 2026vllm Denial of serviceCVE-2026-115918## Summary vLLM's `/v1/responses` endpoint accepts request-level `chat_template_kwargs`, but does not apply the `--trust-request-chat-template` gate that protects Chat Completions, render, tokenize, and pooling paths. When the server is run with the documented default `trust_request_chat_template=False` and no explicit `--chat-template`, a Responses request can pass: ```json {"chat_template_kwargs": {"chat_template": "<attacker Jinja template>"}} ``` That key is preserved by `ChatParams.get_
- 3.4LowOct 26, 2026vllmCVE-2026-115917### Summary The OpenAI-compatible server registers Starlette `CORSMiddleware` with `allowed_origins` defaulting to `["*"]`, and performs no authentication unless `--api-key` (or `VLLM_API_KEY`) is configured. A web page on any origin can send requests to a vLLM server that the victim's browser can reach (for example `localhost` or an internal/VPN address) and read the responses. The default `allow_credentials=False` blocks cookie-bearing cross-origin requests; because vLLM authenticates with a
- 6.5MediumOct 26, 2026vllmCVE-2026-115916For a model whose vocabulary size is an exact multiple of the embedding padding size (64) — e.g. any Llama-2-family model, vocab 32000 — a single request carrying a pre-tokenized prompt with token id equal to the vocab size (32000) passes vLLM's input-id validation but is one past the last embedding row. At tensor-parallel size 1 the embedding lookup does not mask indices, so the id reaches `F.embedding` out of range and raises a CUDA device-side assert, which poisons the engine's CUDA context a
- 8.1HighOct 26, 2026vllmCVE-2026-115915### Summary In vLLM 0.30.0, `ImageMediaIO` passes attacker-controlled image bytes to Pillow's format autodetection without restricting the accepted formats; the request's MIME label does not constrain decoder selection. An EPS payload labeled `image/png` reached the host's Ghostscript executable. On a host with Ghostscript affected by CVE-2024-29510, this exposes the known Ghostscript sandbox escape through vLLM's image-loading path and can execute commands with the vLLM process's privileges. A
- 6.5MediumOct 26, 2026vllmCVE-2026-115914## Summary Any vLLM deployment serving a model of the DeepSeek-OCR family — `deepseek-ai/DeepSeek-OCR`, `deepseek-ai/DeepSeek-OCR-2`, or `baidu/Unlimited-OCR` (whose `UnlimitedOCRForCausalLM` subclasses `DeepseekOCRForCausalLM`) — can be **killed by a single unauthenticated chat request carrying an ordinary, schema-valid PNG image**, under completely default server configuration. The image model's input validation contains a guard inherited from the upstream DeepSeek-OCR reference implementati
- 6.5MediumOct 26, 2026vllm Denial of serviceCVE-2026-115913### Summary The Phi-4 multimodal audio encoder (`phi4mm_audio.py` / `phi4mm_utils.py`) runs its conformer attention in **eager mode by default**: the official HF config of `microsoft/Phi-4-multimodal-instruct` does not set `use_pt_scaled_dot_product_attention`, so the default `False` applies (`phi4mm_audio.py:166`, `:876`; `phi4mm_utils.py:1669`). The eager path fully materializes the attention probability matrix of shape `[n_chunks, 16, 500, 500]` per layer — and then **stores it on the module
- 7.5HighOct 26, 2026vllm DeserializationCVE-2026-115912## Affected - **Ecosystem / package:** pip / `vllm` - **Affected versions:** vLLM < 0.32.0. ## Summary When `--mm-processor-cache-type shm` is enabled, vLLM's multimodal SHM cache represents a cached item with an `address` and `monotonic_id` pair and treats that pair as authority to dereference shared memory in the worker. A public scale-out request can supply its own multimodal `features.kwargs_data`, so an authenticated caller can forge an inner SHM carrier that points at attacker-controlle
- 6.5MediumOct 26, 2026vllm Denial of serviceCVE-2026-115911### Summary vLLM renders chat templates by passing the resolved Jinja2 source to `tokenizer.apply_chat_template()`, which compiles and `.render()`s it in an `ImmutableSandboxedEnvironment`. The sandbox prevents code-execution escapes but imposes **no wall-clock timeout, no output-size cap, and no nested-loop or binop limit**. The render runs in a `ThreadPoolExecutor` whose `max_workers` defaults to **1**, and CPython worker threads cannot be interrupted. An authenticated API client (or a malicio
- 6.5MediumJul 6, 2026vllmCVE-2026-55514vLLM 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 /v1/completions request can make such a request and induce a crash. This issue is fixed in version 0.24.0.
- 7.5HighJul 6, 2026vllmCVE-2026-54234vLLM 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 the engine selects the next live token for a request and is written back into the drafter's input ids; that out-of-vocabulary value is later consumed by the model's embedding and
- 6.5MediumJul 6, 2026vllm Denial of serviceCVE-2026-55646vLLM 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 size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allo
Top products
- vllm11 CVEs in the last year
Counts cover CVEs and advisories Watch Floor tracks, by the date they became news. Updated every 10 minutes.