Improper Validation of Array Index Affecting vllm package, versions [0.22.0,0.24.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-VLLM-21707828
- published25 Oct 2026
- disclosed25 Oct 2026
- creditRex Liu
Introduced: 25 Oct 2026
NewCVE-2026-116174 (opens in a new tab)How to fix?
Upgrade vllm to version 0.24.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Improper Validation of Array Index via the Rust gRPC Generate and GenerateStream service handlers in rust/src/server/src/grpc/convert.rs, which map prompt.token_ids values from the protobuf TokenIds field directly to Prompt::TokenIds without validating them against the served model or tokenizer vocabulary. An attacker can submit a request containing out-of-vocabulary prompt.token_ids values, which are forwarded unchecked to EngineCore, triggering a fatal embedding lookup failure that terminates EngineCore and leaves the server unhealthy. The Rust OpenAI and HTTP /inference/v1/generate routes already apply token-id range validation, but no equivalent guard exists on the gRPC path.