Vllm - vulnerabilities (CVEs)

121 CVEs in 2 products, 37 in the last 30 days, newest from 2026-10-26.

Products

• Vllm - 120 CVEs
• Aibrix - 1 CVEs

Newest CVEs of Vllm

• CVE-2026-115918 - CVSS 6.5 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. From 0.16.0 until 0.32.0, the /v1/responses endpoint allows an authenticated caller to…
• CVE-2026-115917 - CVSS 4.7 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the OpenAI-compatible server configures Starlette CORSMiddleware with…
• CVE-2026-115916 - CVSS 6.5 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper…
• CVE-2026-115915 - CVSS 9.8 (critical), 2026-10-26: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, ImageMediaIO passes attacker-controlled image bytes to Pillow through…
• CVE-2026-115914 - CVSS 6.5 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path…
• CVE-2026-115913 - CVSS 6.5 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, the Phi-4 multimodal audio encoder in phi4mm_audio.py and phi4mm_utils.py…
• CVE-2026-115912 - CVSS 8.8 (high), 2026-10-26: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, an authenticated caller can place forged shared-memory address and…
• CVE-2026-115911 - CVSS 6.5 (medium), 2026-10-26: vLLM is an inference and serving engine for large language models. From 0.19.0 until 0.32.0, authenticated callers can supply a request chat template when no…
• CVE-2026-116181 - CVSS 7.1 (high), 2026-10-25: 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…
• CVE-2026-116180 - CVSS 8.3 (high), 2026-10-25: 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…
• CVE-2026-116179 - CVSS 8.7 (high), 2026-10-25: 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…
• CVE-2026-116178 - CVSS 8.2 (high), 2026-10-25: 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…
• CVE-2026-116177 - CVSS 8.7 (high), 2026-10-25: vLLM from 0.10.2 before 0.25.0 contains an uncontrolled resource consumption vulnerability that allows unauthenticated attackers to exhaust memory because the…
• CVE-2026-116176 - CVSS 8.8 (high), 2026-10-25: 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…
• CVE-2026-116175 - CVSS 7.1 (high), 2026-10-25: vLLM from 0.19.0 before 0.24.0 contains a decompression bomb vulnerability because the AudioMediaIO multimodal path calls load_audio without the…
• CVE-2026-116174 - CVSS 8.2 (high), 2026-10-25: 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…
• CVE-2026-116173 - CVSS 8.2 (high), 2026-10-25: 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…
• CVE-2026-116172 - CVSS 8.2 (high), 2026-10-25: 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…
• CVE-2026-114055 - CVSS 8.7 (high), 2026-10-21: vLLM from 0.7.3 before 0.31.0 contains an uncontrolled resource consumption vulnerability that allows remote clients to control multimodal processor…
• CVE-2026-114054 - CVSS 7.1 (high), 2026-10-21: vLLM before 0.31.0 contains a cache aliasing vulnerability that allows authenticated attackers to collide shared cache keys by supplying caller-controlled…
• CVE-2026-114053 - CVSS 9.2 (critical), 2026-10-21: 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…
• CVE-2026-114052 - CVSS 8.7 (high), 2026-10-21: 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…
• CVE-2026-114051 - CVSS 7.5 (high), 2026-10-21: 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…
• CVE-2026-114050 - CVSS 7.5 (high), 2026-10-21: 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.…
• CVE-2026-114049 - CVSS 6.3 (medium), 2026-10-21: 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…
• CVE-2026-109311 - CVSS 7.1 (high), 2026-10-12: vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser heap overflow.…
• CVE-2026-105922 - CVSS 5.3 (medium), 2026-10-06: A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file…
• CVE-2026-105760 - CVSS 5.3 (medium), 2026-10-05: 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…
• CVE-2026-105759 - CVSS 7.5 (high), 2026-10-05: 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…
• CVE-2026-105758 - CVSS 5.3 (medium), 2026-10-05: vLLM is an inference and serving engine for large language models. From 0.24.0 until 0.30.0, the Qwen2VLVideoBackend and Qwen3VLVideoBackend classes accept…