Sound the depths of every vulnerability.

▾ Sunlitvllm · vllmEPSS 0.31%via OSV

vLLM: DoS via unbounded chat_template Jinja2 rendering exhausts the renderer thread pool

CVE-2026-115912High· 7.5

▾ Twilightvllm · vllmEPSS 0.51%via OSV

vLLM: Public multimodal SHM handle forgery reaches worker-side `pickle.loads()` with insecure serialization disabled

CVE-2026-115913Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.33%via OSV

vLLM: Phi-4 multimodal audio encoder materializes and retains full attention matrices: a single max-length audio OOM-crashes the vLLM engine

CVE-2026-115916Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.31%via OSV

vLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)

CVE-2026-115917Low· 3.4

▾ Sunlitvllm · vllmEPSS 0.24%via OSV

vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server

CVE-2026-115915High· 8.1

▾ Twilightvllm · vllmEPSS 0.66%via OSV

vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE

CVE-2026-115914Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.40%via OSV

vLLM DeepSeek-OCR image processing vulnerable to denial of service

CVE-2026-115918Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.35%via OSV

vLLM: Responses API bypasses trust_request_chat_template for chat_template_kwargs

CVE-2026-116173High· 7.5

▾ Twilightvllm · vllmEPSS 0.34%via OSV

vLLM from 0.22.0 before 0.24.0 contains a denial of service vulnerability that allows remote attackers to terminate EngineCore by bypassi…

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…

CVE-2026-116178High· 7.5

▾ Twilightvllm · vllmEPSS 0.33%via OSV

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 inc…

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 re…

CVE-2026-116176High· 8.2

▾ Twilightvllm · vllmEPSS 0.32%via OSV

vLLM from 0.9.2 before 0.24.0 contains a server-side request forgery vulnerability that allows API callers to force outbound connections …

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 pref…

CVE-2026-114050Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.20%via OSV

vLLM: Forged multimodal UUID + P0/P1 processor-cache eviction drift: unauthenticated remote crash of the whole vLLM engine

GHSA-f623-hjm8-5wg5Critical· 8.1

▾ Midnightvllm · vllmvia GHSA

Duplicate Advisory: vLLM: Request-controlled mm_processor_kwargs.code_revision allows remote code execution

GHSA-hfwf-hgvp-4rr8High· 7.5

▾ Twilightvllm · vllmvia GHSA

Duplicate Advisory: vLLM vulnerable to remote denial of service through forged multimodal UUID cache desynchronization

GHSA-3cgq-c484-rx5jHigh· 7.5

▾ Twilightvllm · vllmvia GHSA

Duplicate Advisory: vLLM 0.7.3 before 0.31.0 DoS via Unvalidated mm_processor_kwargs

CVE-2026-105922Medium· 4.3PoC⚖ disputed

▾ Twilightvllm · vllmEPSS 0.31%via NVD

A security flaw has been discovered in vllm-project vLLM up to 0.31.0

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 vllm/model_executor/layers/utils.py of the component Penalty Handler. Performing a manipulation re…

CVE-2026-105760Medium· 5.3

▾ Sunlitvllm · vllmEPSS 0.30%via NVD

vLLM is an inference and serving engine for large language models

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 wit…

CVE-2026-105759Medium· 5.9PoC

▾ Twilightvllm · vllmEPSS 0.41%via NVD

vLLM is an inference and serving engine for large language models

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 una…

CVE-2026-105758Medium· 5.3

▾ Sunlitvllm · vllmEPSS 0.30%via NVD

vLLM is an inference and serving engine for large language models

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 request-level values for the media_io_kwargs.video.max_frames and media_io_kwargs…

CVE-2026-105757Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.31%via NVD

vLLM is an inference and serving engine for large language models

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, structured-output request failures can escape request-scoped validation and reach the EngineCore fatal-error path. A per-request backend mismatch can re-…

CVE-2026-105756Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.33%via NVD

vLLM is an inference and serving engine for large language models

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServ…

CVE-2026-105755Medium· 4.2

▾ Sunlitvllm · vllmEPSS 0.20%via NVD

vLLM is an inference and serving engine for large language models

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. …

CVE-2026-105754Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.27%via NVD

vLLM is an inference and serving engine for large language models

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifi…

CVE-2026-105753Medium· 6.5

▾ Sunlitvllm · vllmEPSS 0.43%via NVD

vLLM is an inference and serving engine for large language models

vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a media hash in the frontend sender cache during multimodal rendering and before engine admission, w…

CVE-2026-105752Low· 3.1