CVE-2026-114051High· 7.5▾ TwilightvLLM 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. Unauthe…
▾ Twilight zone — High severity, or a signal on a lesser flaw
impact 41.3 · likelihood 0 · exploitation 0
Need a working PoC? Pro members can cast a request and our team develops one — it lands right here.
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.
vllm < 0.31.0Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-105922Medium· 4.3A security flaw has been discovered in vllm-project vLLM up to 0.31.0
CVE-2026-105757Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-105756Medium· 6.5vLLM is an inference and serving engine for large language models
CVE-2026-94622High· 7.5vLLM versions through 0.29.0 contain a denial of service vulnerability in the NIXL connector's metadata handling for prefill/decode disaggregated deployments
CVE-2026-114049Low· 3.7vLLM before 0.31.0 Stale allowed_token_ids Mask via InputBatch.condense
CVE-2026-114052High· 7.5vLLM 0.25.0 before 0.31.0 MOSS-Audio Memory Exhaustion via /tokenize mm_processor_kwargs