Veille CVE

Semaine du 19 octobre au 25 octobre 2026

7 CVE

Critique 0 Élevée 5 Moyenne 1 Faible 1 Non évaluée 0 Exploitées (KEV) Tri : plus récentes « vllm-project vllm » ✕
  1. CVE-2026-114055 7.5 Élevée

    vllm-project vllm

    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.

  2. CVE-2026-114054 6.5 Moyenne

    vllm-project vllm

    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.

  3. CVE-2026-114053 8.1 Élevée

    vllm-project vllm

    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.

  4. CVE-2026-114052 7.5 Élevée

    vllm-project vllm

    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.

  5. CVE-2026-114051 7.5 Élevée

    vllm-project vllm

    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.

  6. CVE-2026-114050 7.5 Élevée

    vllm-project vllm

    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.

  7. CVE-2026-114049 3.7 Faible

    vllm-project vllm

    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.