Threats affecting pkg:cargo/vllm-project/vllm

vLLM versions from 0.22.0 up to but not including 0.24.0 have an improper input validation vulnerability in the Rust gRPC Generate and GenerateStream services. This flaw allows attackers to submit out-of-vocabulary prompt token IDs, causing a fatal embedding lookup failure that terminates the EngineCore process and leaves the server in an unhealthy state.

vLLM versions from 0.22.0 up to but not including 0.24.0 have an improper input validation vulnerability in the Rust gRPC converter. This flaw allows remote attackers to bypass max_logprobs limits by sending oversized or integer-wrapping top_n values in CandidateTokens.top_n. Exploiting this can cause torch.topk failures that terminate the EngineCore process.

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 unauthenticated attacker can send unique arbitrary method tokens to unguarded routes such as /tokenize, causing Prometheus's Family::get_or_create function to permanently create counter and histogram label sets. Those label sets increase process memory usage and enlarge the /metrics response until the service or monitoring path is exhausted. This issue is fixed in version 0.30.0.

CVE-2026-103241 is a denial of service vulnerability in the vllm-project vLLM software affecting versions 0.1 through 0.26.0. The flaw exists in the Gemma4UnifiedParser component within the rust/src/parser/src/unified/gemma4.rs file. An attacker can remotely trigger this vulnerability to cause a denial of service. A patch is available in version 0.29.1rc0, which addresses this issue.

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

vLLM through 0.29.0 fetches and fully materializes remote or inline media before enforcing its documented media controls (the VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed-audio size cap, default 25 MB, and the per-modality --limit-mm-per-prompt item limits). Across four ingress paths — the shared media-acquisition layer (HTTPConnection.get_bytes()/async_get_bytes()), the chat completions audio_url/base64 path, the batch speech runner, and the Rust frontend POST /tokenize route — the server reads the entire HTTP response body, base64-decodes the inline payload, or spawns one fetch/decode task per media part, and only then applies the limit (or, on some paths, never applies it). A remote attacker can therefore cause the API server or batch-runner process to allocate memory and consume outbound bandwidth proportional to an attacker-chosen body size or media item count before the request is rejected, resulting in pre-inference memory and bandwidth exhaustion (denial of service). The chat and batch surfaces require an API key when one is configured; the Rust frontend /tokenize route is unauthenticated by design. There is no code execution or data disclosure impact.

A security flaw has been discovered in vllm-project vLLM up to 0.29.0. The affected element is the function TiktokenTokenizer::new of the file rust/src/text/src/backend/hf/mod.rs of the component tiktoken vocab File Handler. The manipulation results in denial of service. The attack is only possible with local access. The exploit has been released to the public and may be used for attacks. The pull request to fix this issue awaits acceptance.