Search

Use the Query Builder to create your own search query, or check out the documentation to learn the search syntax.

Search Examples

CVEs in KEV CVEs with EPSS >= 80% Crit. Microsoft High Apache SQL Injection (CWE-89) Linux Kernel High (CVSS 3.1) Apache Struts RCE (Remote Code Execution) XSS (CWE-79) Critical (CVSS 4.0) CVEs to check

Search Results (89 CVEs found)

Export CSV
CVE Vendors Products Updated CVSS v3.1
CVE-2026-116172 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 5.9 Medium
vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC converter that allows remote attackers to bypass max_logprobs limits via CandidateTokens.top_n. Attackers can send Generate or GenerateStream requests with oversized or integer-wrapping top_n values to trigger torch.topk failures that terminate EngineCore.
CVE-2026-116173 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 5.9 Medium
vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassing logprob_token_ids limits in the Rust gRPC frontend. Attackers can send Generate or GenerateStream requests with output_logprobs enabled and more than 128 output_candidates.token_ids, triggering a fatal sampler exception that crashes the engine.
CVE-2026-116174 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 5.9 Medium
vLLM from 0.22.0 before 0.24.0 contains an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream service that forwards unchecked prompt token IDs to EngineCore. Attackers can submit requests with out-of-vocabulary prompt.token_ids values to trigger a fatal embedding lookup failure that terminates EngineCore and leaves the server unhealthy.
CVE-2026-116175 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 6.5 Medium
vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls load_audio without the max_duration_s decoded-duration limit. Authenticated attackers can send small compressed audio via input_audio or audio_url in /v1/chat/completions requests that expands to huge decoded PCM, exhausting server memory.
CVE-2026-116176 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 8.2 High
vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections by embedding a decode address in the X-Request-Id header. Attackers can make a P2pNcclConnector prefill worker ZMQ-connect to an attacker host, leaking the NCCL unique_id and KV-cache tensors or blocking the worker.
CVE-2026-116177 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 7.5 High
vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the Nemotron-VL processors globally set Image.MAX_IMAGE_PIXELS to None. Attackers can submit a pathological decompression-bomb image to /v1/chat/completions to OOM-kill the worker and deny service to co-tenants.
CVE-2026-116178 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 5.9 Medium
vLLM from 0.20.0 before 0.30.0 contains a denial of service vulnerability that allows remote attackers to crash the engine by sending inconsistent multimodal metadata to the disaggregated /inference/v1/generate endpoint. Attackers can replay a valid multimodal item with repeated or overlapping mm_placeholders ranges or mismatched kwargs_data and mm_hashes lists, producing a negative text span in Qwen2.5-VL position construction that terminates the engine.
CVE-2026-116179 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 7.5 High
vLLM from 0.18.0 before 0.31.0 contains a resource exhaustion vulnerability that allows API clients to bypass the video/jpeg frame-count cap by overriding num_frames through media_io_kwargs. Attackers can set num_frames to -1 with a large inline video so VideoMediaIO.load_base64 decodes every frame, exhausting memory and crashing the API frontend.
CVE-2026-116180 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 7.7 High
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
CVE-2026-116181 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-25 6.5 Medium
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop_token_ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.
CVE-2026-114052 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 7.5 High
vLLM after 0.24.0 and before 0.31.0 contains a memory exhaustion vulnerability in MOSS-Audio model serving that caches a processor for every distinct request-controlled mm_processor_kwargs value in an unbounded dictionary. Unauthenticated attackers can send distinct or oversized mel_config values to the /tokenize endpoint, which bypasses --api-key, to exhaust host memory and crash the API process.
CVE-2026-114051 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 7.5 High
vLLM before 0.31.0 skips the min_tokens <= max_tokens check for /inference/v1/generate requests with a null max_tokens, so the EngineCore input thread later dies on an uncaught VLLMValidationError while /health still returns 200. Unauthenticated remote attackers can send one request with an oversized min_tokens to hang all subsequent generation requests until manual restart.
CVE-2026-114053 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 8.1 High
vLLM from 0.7.3 before 0.31.0 forwards the request-supplied mm_processor_kwargs.code_revision to Transformers AutoProcessor.from_pretrained, letting clients select which revision of a model's dynamic processor code is imported when trust_remote_code is enabled. An attacker controlling a revision in the served model repository can send a multimodal request to the unauthenticated /tokenize endpoint to execute arbitrary Python in the vLLM API process.
CVE-2026-114049 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 3.7 Low
vLLM before 0.31.0 contains a cross-request mask leak in InputBatch.condense() that allows remote attackers to constrain other clients' outputs by leaving stale allowed_token_ids rows. Attackers can submit concurrent constrained generate requests, including via unauthenticated /invocations, so recycled batch slots apply their token allowlist to victims' unrestricted requests.
CVE-2026-114050 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 7.5 High
vLLM before 0.31.0 uses a client-supplied multimodal uuid verbatim as cache identity with no consistency check on cache hits, allowing engine crashes. Unauthenticated attackers can desynchronize the P0/P1 processor caches to trigger a fatal token-placeholder mismatch, killing the entire serving instance until restarted.
CVE-2026-114054 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 6.5 Medium
vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled values such as EXIF ImageID or cache_salt. Attackers can set a UUID EXIF ImageID to receive another request's cached processed media, or match cache_salt to a LoRA name to reuse first-block KV state.
CVE-2026-114055 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-22 7.5 High
vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor parameters by supplying per-request mm_processor_kwargs. Attackers can set large image size, patch count, crop count, or frame count values in Isaac, InternVL, H2OVL, and other processors to exhaust memory and terminate the shared server.
CVE-2026-105759 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-16 5.9 Medium
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the Rust frontend's track_http_metrics middleware records the raw HTTP method token as a Prometheus label for requests reaching registered routes. An unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.
CVE-2026-105760 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-16 5.3 Medium
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, a caller can use the request-level media_io_kwargs field to select the GLMGA video backend and supply large values for the fps and max_frames options without a strict work ceiling. GLMGA constructs and deduplicates an attacker-sized pre-decode frame-index list, allowing a compact request and tiny valid video to consume disproportionate CPU time and memory in the shared media-loading executor. This issue is fixed in version 0.30.0.
CVE-2026-73557 2 Vllm, Vllm-project 2 Vllm, Vllm 2026-10-15 5.3 Medium
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 /v1/chat/completions through AsyncMultiModalItemTracker.resolve_items, asyncio.gather, and the default executor, allowing an invalid sparse tensor to reach tensor.to_dense despite the CVE-2025-62164 guard when enable_prompt_embeds is enabled. This issue is fixed in version 0.26.0.