Vllm-Project
Vulnerability activity for Vllm-Project: what is being exploited, what was published lately, and when the next patch release is due.
Last 30 days
- CVEs
- 13
- Critical (CVSS 9+)
- 0
- Exploited (CISA KEV)
- 0
- With exploit code
- 0
Last 90 days
- CVEs
- 13
- Critical (CVSS 9+)
- 0
- Exploited (CISA KEV)
- 0
- With exploit code
- 0
Last 365 days
- CVEs
- 13
- 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 25, 2026Vllm-Project vllmCVE-2026-116181vLLM 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.
- 7.7HighOct 25, 2026Vllm-Project vllm Memory corruptionCVE-2026-116180vLLM 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.
- 7.5HighOct 25, 2026Vllm-Project vllm Denial of serviceCVE-2026-116179vLLM 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.
- 5.9MediumOct 25, 2026Vllm-Project vllm Denial of serviceCVE-2026-116178vLLM 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.
- 7.5HighOct 25, 2026Vllm-Project vllm Denial of serviceCVE-2026-116177vLLM 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.
- 8.2HighOct 25, 2026Vllm-Project vllm SSRFCVE-2026-116176vLLM 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.
- 6.5MediumOct 25, 2026Vllm-Project vllmCVE-2026-116175vLLM 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.
- 5.9MediumOct 25, 2026Vllm-Project vllmCVE-2026-116174vLLM 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.
- 5.9MediumOct 25, 2026Vllm-Project vllm Denial of serviceCVE-2026-116173vLLM 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.
- 5.9MediumOct 25, 2026Vllm-Project vllmCVE-2026-116172vLLM 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.
- 6.5MediumOct 21, 2026Vllm-Project vllm Auth bypass / access controlCVE-2026-114054vLLM 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.
- 7.5HighOct 21, 2026Vllm-Project vllmCVE-2026-114051vLLM 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.
- 3.7LowOct 21, 2026Vllm-Project vllmCVE-2026-114049vLLM 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.
Top products
- vllm13 CVEs in the last year
Counts cover CVEs and advisories Watch Floor tracks, by the date they became news. Updated every 10 minutes.